Blog · Page 6
Field notes.
Page 6 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
Competing on groundedness, not features
Opinion. The AI proposal category is running a feature race. The only durable edge for an AI-native tool is whether its outputs are traceable — and that is not a feature you ship. It is a posture you hold.
Win-loss, Part 5 of 5: the eighteen-month view
Eighteen months of running a win-loss program for ourselves. What we'd change if we started over today, what we wouldn't, and the one investment that compounded more than we expected.
Federal FY Q2 prep weekend
A two-hour weekend checklist for a team about to enter the March federal spike. What to reconfirm, what to clear off the plate, what to tell your SMEs.
Win themes, one year after we published the field guide
The field guide held up on most counts and was wrong on two. What I'd rewrite today, what I wouldn't, and the one test that keeps earning its place.
The DDQ evidence-provenance API
External auditors can now walk from a DDQ answer back to the source evidence without opening the KB. The endpoints, the auth model, and what we hardened before shipping.
Win-loss, Part 4 of 5: closing the KB feedback loop
How a debrief finding becomes a block edit that ships into the next bid. The review cadence that makes it stick. The specific anti-patterns that break the loop.
The prompt test suite, an update
300 tests across our drafting and verification prompts. What they cover, what they miss, which ones still flake, and how we keep the flaky ones from becoming the reason we stop running CI.
Team KPIs we stopped tracking
Two proposal-team metrics we killed this year. Why each one misread the work, and what we replaced them with. Short, opinionated, written from my own dashboard.
A cross-cut of 30 municipal RFPs
Patterns in sub-state procurement across 30 municipal RFPs posted in Q4 2025. Where buyer-side guidance is catching up to federal norms, where it's still behind, and what the data says for a vendor deciding whether to chase this tier.
The weekly DDQ evidence-freshness sweep
A 20-minute weekly routine that catches stale evidence links before a reviewer does. What the sweep covers, what it skips, and why we recommend it for teams that answer more than one DDQ a month.
Competitive moves in Q1 2026, a running log
What Loopio, Responsive, and AutogenAI announced in Q1 2026. What we shipped against them. Opinion piece — I'm the founder, this is my read on the market.
One year of grounded retrieval: what changed, what didn't
The engineering companion to the founder retrospective. A year of build-log posts, condensed: what the retrieval stack looks like now, how verification evolved, what the gold set became, and what's still unsolved.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.