A signals-to-outreach pipeline for public-sector sales
NationGraph helps B2G sellers catch public-sector buying signals before RFPs hit the street — board meetings, budget filings, leadership changes. We built the worker that turns those signals into FOIA requests, contact intelligence, and drafted outreach automatically, reclaiming roughly 30 hours per rep per month.
- Time reclaimed
- ~30 hrs/rep/mo
- Signals/day
- ~14K
- Districts covered
- ~13,400
- Outreach drafted
- Same-day
New signals today
146
+18%
Districts in feed
14
+2
Drafted outreach
9
auto
FOIA pending
23
5 ETA today
Today's signal heatmap
Signal feed
Cook County, IL
IT budget filing · CIO named · technology line item
Round Rock ISD, TX
Board agenda · RFP for student-experience platform
Maricopa County, AZ
Vendor disclosure list updated — 3 new categories
San Diego City, CA
Open RFI · K-12 cybersecurity assessment
Multnomah County, OR
Leadership change · new CTO announced
Mecklenburg County, NC
Procurement officer change · vendor portal updated
Cook County, IL — $4.2M IT earmark
FY26 budget line item for "cybersecurity modernization" with named CIO. RFP estimated within 60–90 days.
Verified procurement contact
Janelle Rivera
CIO · 7 yrs tenure · LinkedIn verified
FOIA queue
3 of 23Travis County, TX
Vendor list 2024
Cook County, IL
IT roster + reports
Wake County, NC
Procurement contracts
Drafted email
✨ AI-generatedTo: jrivera@cookcounty.gov
Subject: Re: FY26 cybersecurity modernization
Hi Janelle — saw the budget filing earmarking $4.2M for cybersecurity modernization at last week's board…
The brief
Public-sector sales has a peculiar shape: the most important information is publicly available but scattered across board minutes, budget filings, FOIA-able vendor lists, and leadership turnover announcements across roughly 13,000 SLED entities. Reps spend a meaningful fraction of their week pattern-matching these sources for signals their competitors haven't seen yet.
The bet: a queue-driven worker that watches every relevant public source, extracts signals, files the right FOIA requests automatically, and surfaces ready-to-send outreach would compress that week of work into a 30-minute morning briefing.
What we built
A continuously-running signal extraction pipeline that processes board-meeting minutes, agenda packets, budget appropriations, vendor disclosures and procurement filings as soon as they are published. An LLM layer extracts structured signals — district X just earmarked $Y for Z — and pushes them into a CRM-ready feed with a confidence score and a citation back to the source document.
For signals that require additional public information, the system auto-drafts the relevant FOIA request and queues it for human review. Once filed, the worker tracks the request through to fulfillment and ingests the response back into the signal graph.
The outreach module composes a personalized first-touch email per signal — referencing the specific board meeting or budget line, named to the right procurement contact, drafted in the rep's existing voice. The rep reviews, edits if they want, sends.
Outcome
Reps reclaim roughly 30 hours per month that were previously research time. The pipeline processes ~14,000 signals a day across ~13,400 districts. Same-day signal-to-drafted-outreach is the default — the rep's morning briefing is, in effect, prospecting done, ready for review.
NationGraph's customers now compete not on who can read the most board minutes — but on who can act on them first.
"We turned a rep's research week into a 30-minute morning briefing."
Keep exploring.
Book a callA modern policyholder portal for a 75-year-old insurance co-op
Co-operators is one of Canada's largest insurance co-operatives — 600+ locations, generations of customer trust, and a legacy self-service experience built around PDFs and phone trees. We rebuilt the policyholder portal around real-time claim status, digital ID cards, and a single-tap "file a new claim" flow that absorbs roughly a third of the inbound contact-centre volume.
- Inbound call reduction
- ~28%
- Time-to-claim filed
- 4 min
An "Ask your vault" AI layer for wealth-management advisors
FutureVault sits at the centre of how RIAs organise client documents — estate, tax, insurance, identity. We built a retrieval-grounded AI layer on top, letting an advisor ask plain-English questions across an entire household's document history and get cited answers in seconds instead of digging through folders.
- Document lookup
- 3.2× faster
- Citation accuracy
- ~96%