Blog · Page 10
Field notes.
Page 10 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
What we learned analyzing 90 days of search logs
Three patterns in the KB-search query logs we did not expect, and one UX change we made because of the findings. Notes from a quarterly log review, written in the build-log spirit.
A composite customer conversation, and the backlog decision it would drive
A distillation of the conversations we have been having with mid-market proposal teams during product development. Composite, not a transcript. The shape of one discoverability problem and how it moves a decision in the backlog.
Healthcare RFP trends for 2026, early read
Seven clauses that were not in 2025 healthcare RFPs and are now showing up repeatedly in the Q4 2025 sample. What they tell us about buyer priorities for the year ahead, with sourcing where it is public.
Shipped: keyboard-first KB search
A small thing that power users have been asking for since month three. Keyboard-first KB search with a reachable command palette, typed result filtering, and no mouse required to open, navigate, and act on a chunk.
Three exec summaries I rewrote this week, part 9
The January installment of the rewrite series. A public-sector services bid, a SaaS renewal proposal, and a financial-services DDQ opener. Three before-and-afters and what each rewrite was actually doing.
When two citations disagree: how the draft resolves it
Two KB chunks say different things about the same claim. The conflict-resolution logic that decides which one the drafted answer cites — when to prefer newer, when to prefer higher-authority, and when to refuse.
Annual planning for proposal teams: the three-sheet model
A three-sheet annual plan — bid forecast, capacity forecast, skill-gap sheet — that a small proposal team can build in a week and revise quarterly. Due by mid-January if you want it to matter.
Observability for drafting: traces, logs, and replays
How we debug a bad draft six weeks after the fact. The three-layer observability stack — request traces, retrieval logs, and deterministic replays — that makes post-hoc drafting issues tractable.
The roadmap bet we rejected
One feature customers asked for through most of year one that we declined to build, and the reasoning. A short founder note on saying no to the thing that would have been popular and wrong.
Procurement budget forecasts for 2026
An early read on federal, state, and enterprise procurement budgets for 2026. Where the RFP dollars are moving, what categories are expanding, and what that implies for the proposal teams covering them.
The January proposal-pipeline reset
A 90-minute ritual for the first working Saturday of the year. Archive finished bids, retire dead opportunities, and prune the active list. The point is a pipeline that reflects what you will actually work on in Q1.
What we learned shipping year one
The post-mortem for twelve months of building PursuitAgent in public. Three things that worked, three things we got wrong, the counterfactuals we wish we had tested, and the bets we are making in year two.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.