The corpus is the single most important competitive asset in this pipeline. Every other tool — DiscoLike, Apollo, Claude — is available to any competitor. The corpus is not. It is built from primary authoritative sources in the energy industry, structured into modules that Claude reads before making any scoring or classification decision, and it grows automatically every week as new information enters the market.
Without the corpus, Claude scores a "Gas Originator" the same way it would score a "Sales Manager" — by title seniority only. With the corpus, Claude knows that a Gas Originator at a mid-size European utility controls spot cargo decisions worth tens of millions annually, reports to the Head of Trading, has budget authority without procurement approval below a certain threshold, and is typically reachable directly because they operate in a high-autonomy environment. That difference is worth everything in outbound.
Generic AI tools hallucinate energy industry nuance. They confuse a Drilling Engineer (technical, not a buyer) with a Drilling Manager (operational buyer). They think "FPSO contract" and "land rig contract" are similar signals. They don't know that a Colombian PSC award means an operator will need land rigs within 18 months. The corpus fixes this by injecting verified, structured domain knowledge at the moment of decision.
Corpus Structure — 5 Modules
For every relevant energy title: what they do day-to-day, what they buy, who they report to, whether they are buyer / influencer / blocker, typical seniority signals, and how their role differs by sector. Covers 80+ titles across O&G, LNG, power trading, energy services, and consulting.
Technical descriptions of products and equipment relevant to energy sales: rig types and HP classifications, LNG carrier specs, turbine types, metering systems, trading platforms, pipeline infrastructure. Enables the system to know what a buyer actually needs when a company operates certain assets.
Per geography: regulatory environment, NOC dynamics, typical decision-making culture, key operators and service companies, seasonal activity patterns, language and communication norms. Covers Texas/Permian, Colombia/LatAm upstream, European power markets, SE Asia, West Africa.
Per sector: who signs the check, who influences the decision, who blocks it, typical sales cycle length in weeks, what triggers a buying decision, what language resonates. Built from industry research, SPE papers, and procurement patterns documented in trade press.
Classification of news event types by their relevance as buying signals. Maps event type → urgency level → likely buyer persona → recommended outreach timing. Prevents the system from treating all energy news equally — it knows which signals actually matter.
Weekly scrape job pulls from Tier 2 sources (trade press). New content is classified, summarised, and appended to the relevant module. You receive a weekly digest of what was added. Flag anything wrong and it gets excluded. Corpus grows and sharpens over time without manual effort.
Continuously scraped LinkedIn job descriptions across all energy sectors. Claude extracts structured knowledge: role definitions, reporting lines, assets operated, tools used, org structure signals. This module self-builds — every week thousands of new JDs flow in and enrich all other modules automatically. See Layer 0C for full architecture.
Source Tiers & Specific Sources
| Source | Type | What it provides | URL | Trust |
|---|---|---|---|---|
| IEA — Int'l Energy Agency | Regulatory / Research | Global energy market data, forecasts, policy context, sector definitions | iea.org/reports | Tier 1 |
| EIA — US Energy Info Admin | Regulatory / Statistical | US market data, drilling activity, rig counts, storage levels, pricing | eia.gov | Tier 1 |
| FERC — Fed Energy Regulatory | Regulatory | US gas and power market structure, pipeline filings, market participant data | ferc.gov | Tier 1 |
| SPE — Society of Petroleum Engineers | Technical / Academic | Drilling engineering definitions, equipment specs, operational best practices | spe.org/publications | Tier 1 |
| API — American Petroleum Institute | Standards / Technical | Equipment standards, rig classification, well construction definitions | api.org/publications | Tier 1 |
| GIIGNL — LNG industry group | Industry Association | LNG market definitions, cargo specs, terminal data, trade flows | giignl.org/publications | Tier 1 |
| ENTSO-E — European grid | Regulatory / Operational | European power market structure, balancing mechanisms, TSO roles | entsoe.eu/data | Tier 1 |
| ANH Colombia | Regulatory | Colombian upstream contracts, PSC awards, block map, active operators | anh.gov.co | Tier 1 |
| S&P Global Platts | Trade Press | Price benchmarks, deal announcements, market commentary, LNG flows | spglobal.com/commodityinsights | Tier 2 |
| Argus Media | Trade Press | Energy price reporting, deal flow, market structure analysis | argusmedia.com | Tier 2 |
| Rigzone | Trade Press | Rig contracts, drilling market news, equipment specifications, job market | rigzone.com | Tier 2 |
| Upstream Online | Trade Press | O&G project news, operator activity, contract awards, exploration | upstreamonline.com | Tier 2 |
| Oil & Gas Journal | Trade Press | Technical articles, market analysis, refining and petrochemicals | ogj.com | Tier 2 |
| LNG World News | Trade Press | LNG terminal news, shipping contracts, cargo deals, liquefaction projects | lngworldnews.com | Tier 2 |
| Power Magazine | Trade Press | Power generation technology, utility operations, grid developments | powermag.com | Tier 2 |
| Recharge News | Trade Press | Renewable energy, offshore wind, solar projects, green hydrogen | rechargenews.com | Tier 2 |
| Baker Hughes Rig Count | Company Data | Weekly active rig count by country and basin — primary drilling activity signal | bakerhughes.com/rig-count | Tier 3 |
| NOV / Varco Tech Docs | Company Whitepapers | Rig specifications, HP classifications, drillstring equipment definitions | nov.com/resources | Tier 3 |
| SLB (Schlumberger) Publications | Company Whitepapers | Oilfield services definitions, completion techniques, reservoir management | slb.com/resource-library | Tier 3 |
| LinkedIn Jobs — via Apify | Live Industry Data | Continuously scraped job descriptions across all energy sectors — primary source for Module 1 (titles), Module 2 (assets/equipment), Module 4 (org structure), Module 5 (hiring signals). Written by the industry, for the industry. See Layer 0C. | apify: harvestapi | Live Feed |
How the Corpus Gets Built — Process
Most outbound failures start here — at the ICP definition step. A client says "energy companies" and you build a list of energy companies. That list is useless. The interrogation engine exists to prevent this by using the corpus to identify every ambiguity in the client's description and resolve it before any data is pulled.
The engine is powered by Claude, reading the corpus to formulate the right clarifying questions. It is not a static form — it adapts based on what the client says. If they mention "drilling," it knows to ask onshore vs offshore, equipment vs services, operator vs contractor. If they say "trading," it knows to ask physical vs financial, spot vs term, gas vs power vs LNG. Each question is drawn from the corpus — these are exactly the distinctions that change the entire target list.
Forms assume you know what to ask in advance. The corpus-powered dialogue adapts to what the client says. If a client mentions "offshore wind," the system shifts into a completely different question tree than if they said "conventional gas." A form would ask the same 10 questions regardless. This system asks 3–5 targeted questions that actually resolve the specific ambiguities in what that client said.
Example Dialogue — Land Rig Sale (Sofía / Valiat scenario)
Example Dialogue — Sales Agency Services
What the Interrogation Produces
Every energy job description is a primary source document. Written by a hiring manager, reviewed by HR, approved by leadership — it describes in precise industry language exactly what a company does, what assets it operates, what skills it needs, who reports to whom, and what problems it's trying to solve right now. No PR spin, no website vagueness. Pure operational reality.
The Jobs Intelligence Feed harvests this at scale and continuously. Running 24/7 via Apify, it searches LinkedIn for energy sector roles across Power & Utilities, LNG, Trading, O&G, and Energy Services. Each job description is processed by Claude, which extracts structured intelligence across three dimensions: corpus knowledge (what does this title mean, what does this company operate), discovery signal (this company is hiring = they exist, they're active, they have budget), and urgency signal (seniority and function of the role determines how hot the signal is).
Your competitors are scraping the same Apollo databases and Rigzone articles. Nobody is systematically harvesting LinkedIn job descriptions as intelligence. A job posting tells you more about a company than their website does — it reveals the org structure they're building, the technology stack they run, the assets they operate, the problems they can't solve internally. That's the corpus. That's the signal. That's the discovery source. One pipeline, three returns.
Three Simultaneous Purposes
Every JD feeds Module 1 (title definitions), Module 2 (assets/equipment mentioned), Module 4 (reporting lines = org structure), and Module 6 (the jobs module itself). Claude extracts structured entries. The corpus self-builds every week without manual curation.
- Role definitions in industry's own language
- Asset & equipment vocabulary per sector
- Org structure patterns per company type
- Buyer vs influencer vs blocker classifications
Every unique company posting an energy job is a discovery candidate. Companies hiring = companies that exist, are active, and have payroll budget. Cross-referenced against the Companies table — new companies get stub records, known companies get activity flags updated.
- Surface companies not in Apollo or DiscoLike
- Validate that discovered companies are active
- Enrich existing company records with hiring data
- Flag companies in growth mode automatically
The role being hired, its seniority, and its function determine signal strength. A VP Commercial posting = the company is building commercial capacity = they need what EnergyLeads sells. Signal scores feed directly into Layer 7 urgency scoring, pushing high-signal companies to the front of the outreach queue.
- Commercial / BD / Sales roles = highest signal
- C-Suite or VP level = amplified signal
- Multiple simultaneous postings = expansion mode
- Signal decay tracked — active vs closed postings
Pipeline Architecture — How It Runs
harvestapi/linkedin-job-search actor, polls until completion, and fetches the full result set. Handles errors gracefully and resumes from last state. Can run for days or weeks without intervention.hiring_signal = true is set. If no match, a stub company record is created with domain TBD, flagged for enrichment in the next Layer 1 pass. Both operations in a single Airtable batch call.Search Query Library — Energy Sectors
- energy analyst · power trader · grid operator
- utility manager · transmission engineer
- generation manager · energy scheduler
- market analyst energy · regulatory affairs energy
- energy procurement · balancing manager
- TSO analyst · dispatch operator · PPA manager
- renewable energy developer · grid integration engineer
- LNG trader · LNG analyst · LNG commercial
- gas trader · commodity trader energy
- gas marketing · LNG operations
- cargo operations LNG · energy trading analyst
- derivatives trader energy · gas originator
- LNG shipping · terminal operations manager
- gas supply manager · portfolio optimization
- drilling manager · VP drilling · completions manager
- reservoir engineer · production engineer
- asset manager upstream · exploration manager
- petroleum engineer · subsurface manager
- business development oil gas · commercial director E&P
- head of origination · commercial director energy
- VP commercial energy · CCO energy
- business development manager energy
- energy consultant · energy sales director
- head of business development energy
- energy SaaS sales · energy analytics
Airtable Jobs Table — Full Schema
app2c5p6nY5ecstrS · Dedup key: Job IDapify:harvestapiSignal Score Logic
| Condition | Points | Reasoning |
|---|---|---|
| Seniority = C-Suite or VP | +4 | Highest-authority hire = largest growth signal |
| Seniority = Director | +3 | Senior hire, strong expansion signal |
| Seniority = Manager | +2 | Team build-out signal |
| Function = Commercial / Trading / BD | +3 | Direct signal for EnergyLeads ICP — they need pipeline |
| Function = Technical / Operations | +1 | Weaker signal — company is active but not commercial-focused hire |
| Company already in Companies table | +2 | Known target confirming activity |
| Posted within last 7 days | +2 | Recency = urgency |
| Posted within last 30 days | +1 | Still relevant |
| Salary data present | +1 | Company is serious — budget confirmed |
What Claude Extracts Per Job Description
- Role definition — what this person does day-to-day
- Decision authority — what they buy or approve
- Reporting line — who they report to (org structure)
- Assets operated — rigs, terminals, turbines, trading systems
- Technologies required — ETRM platforms, SCADA, SAP, etc.
- Industry vocabulary — exact terms used in this sector
- Buyer classification — buyer / influencer / blocker
- Company activity status — hiring = active + funded
- Growth phase — building vs. replacing vs. expanding
- Commercial intent — are they building a sales/BD team?
- Sector confirmation — what sector does this company actually operate in
- Geography — where are they operating (not just HQ)
- Urgency level — seniority + recency = signal score
Discovery is where the pipeline starts generating data. Four sources run in parallel depending on which input type was provided. The outputs are merged and deduplicated on company domain before anything proceeds to scoring. This means even if the same company appears in DiscoLike results, an Apollo search, and your conference database, it is only processed once.
The key design decision here is running all sources in parallel rather than sequentially. DiscoLike gives you web-based discovery that Apollo misses. Apollo gives you structured firmographic data that DiscoLike lacks. Conference databases give you intent signals (the company showed up at an industry event) that neither tool provides. Combining all three produces a richer, larger, and more varied starting list than any single source.
Sales Navigator indexes LinkedIn profiles, which are incomplete, outdated, and biased toward tech-sector companies. A lot of energy companies — especially mid-size independents, commodity traders, and drilling contractors — have poor LinkedIn presence but detailed, well-maintained websites. DiscoLike reads the actual website text, which means it surfaces companies that Sales Nav systematically misses. In energy specifically, this gap is significant.
Data Fields Produced — per company
signal_score per individual posting.This is the most important cost-control mechanism in the pipeline. Email enrichment costs money per record. Phone enrichment costs money per record. If you enrich every company you discover, you waste most of that spend on companies that will never convert. The scoring layer exists to eliminate this waste by running a cheap Claude API call (approximately $0.002 per company using Haiku) before you spend $0.10–0.50 per contact on enrichment.
The scoring prompt includes the relevant corpus modules for the company's sector, ensuring Claude applies real domain knowledge. A company described as "gas marketing and origination" is not scored the same as a company described as "gas distribution" — even though both would superficially appear in an "Oil & Gas" industry filter on Apollo.
Assume 1,000 companies discovered per run. At $0.30 average enrichment cost per contact (email + phone), enriching all 1,000 costs $300 per run. If scoring eliminates 60% as Tier C, you enrich 400 companies for $120. Over 12 runs per year, scoring saves approximately $2,160 — more than the entire annual cost of the Claude API subscription. The scoring layer pays for itself many times over.
Scoring Dimensions — 7 factors
Is this company in a sector that genuinely needs what the ICP describes? Claude reads the website description + industry tags and cross-references against the corpus sector definitions. Not all "energy companies" score equally — a financial energy hedge fund scores differently from a physical gas originator.
Company size relative to the confirmed ICP headcount range. Companies outside the range score 0 on this dimension. Companies at the edges score partial points. Perfect fit scores full 15. Prevents both targeting companies too small to have budget and too large to need your help.
HQ country and operational geography vs confirmed target regions. Companies headquartered in priority regions score full points. Adjacent regions score partial. Out-of-scope geographies score 0. Regional market context from corpus is used — e.g. Colombian companies get full score for LatAm-focused ICPs.
Evidence from website or data sources that the company has an active commercial/sales function. Companies with "origination", "business development", "commercial" in their description score higher. Corpus knowledge helps identify these signals even when they use industry-specific terminology.
Boolean from Layer 1 — was this company found in the conference database? If yes, full 10 points. This is a strong intent signal: the company spent money to attend or exhibit at an industry event, indicating active market engagement. CERAWeek presence is weighted higher than smaller events.
Recent funding rounds, acquisitions, or major contract awards indicate growth mode — companies spending money to grow are more likely to spend on services that accelerate that growth. Scored based on recency (last 12 months scores full, 12–24 months scores half).
Boolean from Layer 1 — was this company flagged by the Builtin scraper as actively hiring sales or BD roles? For EnergyLeads' own ICP specifically, this is the single strongest buying signal. Full 10 points if active hiring detected, 0 if not.
Tier Definitions
- Strong sector fit + at least 2 positive signals
- Proceed immediately to full enrichment
- AI first line written
- Included in weekly priority digest
- Target: ~15–20% of discovered companies
- Decent fit, fewer signals
- Proceed to enrichment — lower priority
- No AI first line until upgraded
- Contacted in second wave
- Target: ~25–35% of discovered companies
- Poor fit or missing key criteria
- Stored in Airtable but NOT enriched
- No spend, no outreach
- Can be re-evaluated if ICP changes
- Target: ~45–60% of discovered companies
Contact discovery is where most generic tools fail. They return everyone with "Director" or above in their title, regardless of whether those people actually make or influence the purchasing decision for what you're selling. The Job Title Dictionary in the corpus fixes this by providing Claude with precise role definitions for the energy sector.
The distinction between buyer, influencer, and blocker is critical. A Head of Trading at a gas company is a buyer for origination services. A VP of Finance at the same company is a blocker — they can kill deals but won't initiate them. A Commercial Director is both buyer and influencer depending on company structure. Without the corpus, Claude defaults to seniority. With it, it defaults to decision-making role.
Persona Filters — energy sector specific
- Chief Commercial Officer / CCO
- VP Sales / VP Commercial
- Head of Business Development
- Commercial Director / Manager
- Head of Origination / Gas Originator
- Head of Trading / Energy Trader
- Director of Sales / Sales Director
- VP Drilling / Drilling Manager (for rig sales)
- CEO / President (small companies — direct buyer)
- COO (fleet decisions at drilling contractors)
- Asset Manager (operational buying influence)
- VP Operations (approves operational spend)
- Completions Manager (influence on services)
- Reservoir Engineer (technical gatekeeper)
- General Manager (SME — often final decision)
The waterfall pattern is the key architectural decision here. Running all enrichment tools in parallel and taking the best result would cost 5x more per contact. The waterfall runs tools in order of hit rate and cost-efficiency — if the first tool finds the email, you never call the second. This typically results in 60–70% of emails found on the first tool, 20% on the second, and 10% on tools 3–4. The remaining ~10% get no email found.
Catch-all emails require special treatment. A catch-all domain accepts all incoming email regardless of whether the specific address exists — so the email [email protected] appears valid even if that person doesn't exist. Sending to catch-alls damages your sender reputation without generating replies. They are quarantined in a separate Airtable view and processed by Scrubby before any decision to send.
Your sending domains are infrastructure. A damaged domain means every email — not just the bad ones — goes to spam. Verification is the last line of defence before contacts enter Instantly. It adds a few cents per record but prevents the kind of reputation damage that takes 3–6 months and significant effort to recover from.
The quarantine system is important. Risky emails — primarily catch-alls — are not deleted. They sit in a separate Airtable view where you can manually review and decide whether to send. Some catch-all domains are actually fine to send to (large companies that use catch-all as an IT policy). Others are genuinely risky. The quarantine lets you make that call on a case by case basis rather than automatically discarding them or automatically sending to them.
Phone enrichment runs only on Tier A contacts — the top 15–20% of your list. The reasoning is straightforward: phone data costs more per record, and cold calling is a higher-effort, higher-reward activity that only makes sense for the best-fit prospects. Running it on Tier B contacts wastes budget and calling capacity.
Mobile numbers are significantly more valuable than office direct dials in energy. Decision-makers in trading, origination, and senior commercial roles are rarely at a desk — they're in meetings, on trading floors, or travelling. A mobile number reaches them. A direct dial reaches their assistant. The pipeline prioritises mobile and flags direct dials separately so you know which is which before you call.
Signal detection is what separates a static lead list from a living intelligence system. A company that scored Tier B three months ago may have just been awarded a major contract, hired a new CCO, or announced a major expansion. That changes their urgency from "follow up eventually" to "contact this week." Without automated signal detection, you'd miss this entirely or find out too late.
The Signal Dictionary in the corpus is what makes this layer intelligent. Without it, Claude treats "Company X awarded offshore block in Nigeria" the same as "Company X releases Q3 earnings report" — both are news, neither obviously more important than the other. With the corpus, Claude knows the offshore block award means the company will need drilling services within 12–18 months and the person to contact is the VP Drilling or Asset Development Manager. The signal becomes actionable intelligence, not just noise.
The Job Posting Scraper is now fully replaced and superseded by Layer 0C — a continuously running Apify pipeline that harvests LinkedIn job descriptions at scale across all energy sectors. Signal scores are computed per posting and propagated to parent company urgency scores automatically. No manual configuration needed — it runs forever.
- Runs every 6 hours — 4× daily refresh on signal data
- Covers Power & Utilities, LNG, Trading, O&G, Energy Services
- Signal score 1–10 per posting → urgency boost on company record
- Commercial / VP-level postings = highest urgency boost (+25 pts)
- See Layer 0C for full schema, extraction logic, and cost breakdown
Free API returning recent news articles by company name + keyword. Claude classifies each article against the Signal Dictionary to determine relevance and urgency boost. Runs per company weekly.
- Queries: "[company name] contract", "[company name] expansion", "[company name] acquisition"
- Claude classification: relevant signal / irrelevant / corpus update candidate
- Source URL stored for use as outreach hook
Funding round data — company raised Series A, B, growth equity, or strategic investment. Growth capital = expansion mode = budget to spend on new services. Especially relevant for energy tech and services companies.
- Tracked: funding rounds in last 24 months
- Urgency boost: +20 points for round within 6 months, +10 for 6–24 months
Targeted scraper against Rigzone, Upstream Online, LNG World News for contract awards, project announcements, and block awards. These are the most actionable signals in the energy sector — direct indicators of procurement need.
- Rigzone: rig contracts, drilling program announcements
- Upstream Online: PSC awards, exploration licenses, project FIDs
- LNG World News: terminal contracts, cargo deals, liquefaction projects
- Baker Hughes rig count: weekly drilling activity by basin
Signal → Urgency Boost Mapping (from Signal Dictionary)
| Signal Type | Example | Urgency Boost | Recommended Action |
|---|---|---|---|
| PSC / Block Award | "ANH awards block to Operator X in Colombia" | +30 pts | Contact VP Drilling within 2 weeks |
| Hiring sales/BD role | "Head of Business Development" job posted | +25 pts | Lead with commercial capacity angle |
| Hiring VP/C-Suite commercial | "CCO", "VP Commercial" posted — via Layer 0C | +30 pts | Company building commercial leadership — highest urgency |
| Multiple open commercial roles | 3+ postings at same company — via Layer 0C | +20 pts | Expansion mode — contact immediately |
| New energy company discovered | Job posting from company not yet in DB — Layer 0C stub | +15 pts | Trigger full Layer 1–3 enrichment pass |
| Project FID | "Company X takes FID on LNG terminal" | +25 pts | Target Head of Commercial / CCO |
| New funding round | "Company X raises $50M Series B" | +20 pts | Lead with growth-phase angle |
| Executive hire | "Company X appoints new CCO" | +20 pts | Reach out to new executive directly |
| M&A announcement | "Company X acquires smaller operator" | +15 pts | Integration phase creates opportunity |
| Conference presence | Exhibiting at CERAWeek | +10 pts | Reference event in outreach |
| Rig count increase | Baker Hughes: basin rig count up 15% | +10 pts (sector) | All operators in basin benefit |
| Earnings / growth news | "Company X reports record revenue" | +5 pts | Low urgency — monitor only |
Airtable is the persistence layer — the database that accumulates and grows with every pipeline run. Everything upstream processes records temporarily in Python memory. Airtable is where records live permanently. Every output — Instantly CSV, client portal, weekly digest, PDF report — reads directly from Airtable. Change a record in Airtable and every output reflects it immediately.
The two-table structure with a linked field is important. Companies and Contacts are separate records linked by domain. This means you can look at a company and see all its contacts, or look at a contact and see all the company-level data (score, signals, tier) without duplicating that data on every contact record. It also means if a company's tier changes — because they got a big signal — all their contacts automatically inherit that urgency in any filtered view.
domain— unique keycompany_name,website_urlindustry_tags,sector_normalisedheadcount_range,hq_country,hq_cityicp_score(0–100),tier(A/B/C)urgency_score,total_priority_scorescore_breakdown(JSON),ai_reasoningoutreach_angle,signal_summaryactive_signals(JSON array)outreach_this_week(boolean)conference_presence,hiring_signalsource,first_seen,last_updatedlinked_contacts(relationship field)
linkedin_url— unique keyfull_name,first_name,last_nametitle_raw,title_normalised,seniorityrole_type(buyer/influencer/blocker)email,email_status,safe_to_sendmobile_number,direct_diallocation_city,location_countryai_first_line(personalised opening line)outreach_status(not started / in sequence / replied / closed)campaign_tag(which Instantly campaign)sent_to_instantly(boolean + date)reply_received(boolean)linked_company(relationship to Companies table)first_seen,last_updated
- First name, last name
- Email (verified, safe_to_send only)
- Company name, domain
- Job title
- AI-written first line (personalised per contact)
- Company tier (A/B)
- Signal summary (for reference)
- LinkedIn URL
- safe_to_send = true only
- sent_to_instantly = false only
- role_type = buyer first
- Tier A before Tier B
- Sorted by total_priority_score desc
- Separate file for catch-all quarantine
- Primary signal (e.g. "Saw you're hiring a Head of BD")
- Company description (what they actually do)
- Contact's specific role (from Job Title Dictionary)
- Regional context (if relevant)
- Industry-specific terminology (from corpus)
- Never "quick question" or "I" → "we"
- No em dashes
- Lowercase casual tone
- No corporate filler language
- Max 1 sentence — opening line only
- You review before anything goes live
- Total companies in DB by tier (A/B/C)
- New companies added this week
- Companies with active signals (count + list)
- Top 10 highest priority accounts right now
- Sector breakdown of Tier A companies
- Geography heat map of signal activity
- Watchlist accounts — signal status per account
- Outreach pipeline — in sequence / replied / closed
- Filter by sector, geography, tier, signal type
- Click company → full profile with all data
- Export filtered list to CSV directly
- Add company to watchlist from dashboard
- Mark company as "contacted" to track outreach
- Week-over-week signal comparison
- 🔥 This week's top 5 signals (most urgent)
- 🆕 New Tier A companies discovered
- 📋 Watchlist updates (accounts you're tracking)
- 📈 Hiring trend summary (who's building sales teams)
- 🗺️ Geography spotlight (hottest region this week)
- 📊 DB stats (total size, growth, sector breakdown)
- Forward as-is to existing clients as a value-add
- Strip out internal data, send as market intelligence brief
- Customise per client's sector focus before sending
- Use as lead for new client conversations ("here's what we track")
- Eventually package as paid intelligence subscription
- Rows: O&G upstream / LNG / Gas trading / Power / Energy services / Consulting
- Columns: North America / Europe / LatAm / Africa / SE Asia
- Cell value: signal count + intensity score this week
- Color coded: green (hot) → amber → red (cold)
- Week-over-week change arrows
- Know where to focus DiscoLike queries next week
- Know which sectors are in growth mode vs contraction
- Anticipate client needs before they do
- Use as conversation starter in business development
- Proof of intelligence capability in proposals
- Company name + signal type
- 1-sentence signal summary
- Source URL (click to read full article)
- Urgency score boost (+X points)
- Recommended action (who to contact, what to say)
- Direct link to company record in Airtable
- Client prospect you've been warming — new signal = perfect timing
- Account that went cold — re-engage when signal fires
- Competitor's clients — detect when they might be unhappy
- Monitor key accounts for existing clients
- Company name + domain + tier
- Role being hired (title + seniority)
- Job posting date
- Job posting URL
- Suggested outreach angle based on role
- Contacts already in DB for this company
- Most agencies find this manually, if at all
- You have this automated and delivered weekly
- Timing advantage — you reach out while they're still hiring
- Outreach angle is built-in — "help you build pipeline while you recruit"
- Can be delivered to clients as value-add intelligence
- Filter by company tier, sector, geography, signal
- Search by company name or contact name
- View full company profile + all contacts
- Download filtered CSV directly
- Always live — data refreshes automatically
- Password protected per client
- Custom URL — client.energyleads.co/[clientname]
- Company name, sector, location, headcount
- ICP score and tier
- Active signals (current buying signals)
- Key contacts with title + email
- AI reasoning summary (why this account)
- Recommended outreach angle
- Can hide scoring methodology if preferred
- Company name, domain, HQ location
- What they do (from website description)
- Why they're priority (AI reasoning)
- Active signals with dates
- ICP score and tier
- Top 3 contacts with titles
- Recommended outreach angle
- EnergyLeads branded cover page
- Executive summary (market context, methodology)
- Signal heat map for client's sectors
- Company profiles (sorted by priority score)
- Appendix: full contact list per company
- Client name + date on every page
- Company overview (what they do, market position)
- Why they fit the ICP (scored dimensions)
- Current signals (hiring, funding, news) with dates
- Decision-maker contacts with titles and emails
- Suggested outreach hook (1–2 sentences)
- Competitive context if available
- Proposal attachment — "we built this before you signed"
- Meeting prep for client (they're calling this prospect)
- Onboarding — show client the quality of your intelligence
- Upsell — client wants one-pagers on all their top accounts
- Top signals in their sector this week
- New high-priority accounts in their ICP
- Hiring trends relevant to their market
- Deal flow and contract awards
- Regulatory changes in their geography
- Recommended accounts to prioritise this week
- Included free — positions you as intelligence partner, not just list vendor
- Charged separately — $500–2,000/mo as market intelligence subscription
- Used as sales collateral — "here's a sample of what you'd receive"
- Eventual standalone product if demand is there