OPS-24-B1
Marketplace Scraping
Real-time pricing intelligence across 1,200 marketplaces
Resilient scraping with anti-bot routing, SKU normalization and 5-minute price-change webhooks into the client's repricing engine.
2.1Mproducts/day
OPS-24-A4 — Lead Intelligence
Continuous lead intelligence system for a B2B SaaS sales team
Daily multi-source enrichment of 40k+ accounts, intent signals, decision-maker mapping. Hands-off since Q2 2024.
9.4×pipeline
Challenge
The client — a post-Series-C SaaS — had a 6-person SDR team and a signed target to triple pipeline within a year. Scaling through more headcount was expensive (each SDR ≈ $7k/mo fully loaded), and 60% of their time went to manual work: account discovery, contact enrichment, intent signal tracking across five tools.
They had tried the standard path: ZoomInfo + Apollo + Clay + LinkedIn Sales Navigator. Each tool covered 60–70% of the need, data overlapped, no unified view, and license cost was growing faster than productivity.
Approach
We designed a system that replaces the tool layer with one data pipeline: source layer (Apollo API + LinkedIn scraping + vertical media scraping + G2/Capterra signals), normalization layer (deduplication, canonical company IDs, schema), enrichment layer (decision-makers via Hunter + ClearBit fallback + research agent for atypical cases), and scoring layer (intent + fit + recency).
Every morning the system delivers the team a list of 50 priority accounts with a complete picture: who the decision-maker is, what fresh intent signal they have (hiring, role change, opened an offer, media mention), what we know from prior touchpoints, and what exactly to say. The SDR opens an email and acts.
Architecture: Temporal as orchestrator, Playwright for scraping, Claude as research agent (with guardrails and a $0.50/account budget), Postgres + pgvector for long-term memory, Next.js dashboard for the sales team.
Outcome
Quarterly pipeline grew 9.4× within 12 months. The SDR team stayed the same size — the lift came from better targeting and less admin time.
Operating cost of the system (proxies, LLM, infrastructure) plus our maintenance retainer: ~$1,600/mo. The client saved 1.5 SDR FTE (~$10k/mo fully loaded) and dropped 4 tool licenses (~$3.5k/mo).
System has run for 14 months with zero P1 incidents. Three scope modifications in that time — delivered within the retainer.
Stack
TemporalPlaywrightClaude (Anthropic)Apollo APIHunter APIPostgres + pgvectorNext.jsSlack API
Metrics
- 9.4× — Pipeline lift
- 40,200 — Accounts per day
- 63% — SDR time saved
- −71% — Cost vs prior stack
- 14 mo — Autonomous runtime
- 0 — P1 incidents
More cases
Back to case studies ↗OPS-25-C2
Agent Operations
Autonomous research agent for a financial intelligence firm
Goal-driven agent crawling filings, press, social and internal sources — producing structured analyst briefings every morning before 7 AM ET.
−72%analyst hours
OPS-25-D3
Social Operations
Multi-account content & outreach orchestration for a creator network
47 brand accounts, four platforms, one operator console. Scheduling, engagement, analytics and human-in-the-loop review built end-to-end.
11.6×output
Similar problem in your business?
Every project is different, but patterns repeat.
If you recognise pieces of this case study in your own situation — write. We usually see in the first call whether it is hours-per-week scale or months of infrastructure.