Blog · Page 2
Field notes.
Page 2 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
The federal task-order RFP wave of 2026
IDIQ task-order patterns from the first half of 2026. How response windows, page caps, and evaluation schemes have shifted — and how teams are staffing against them.
The Saturday KB hygiene drill
Thirty-five minutes of knowledge-base maintenance that keeps Monday's drafts from citing stale content. A year in, here's the drill that actually stuck.
April DDQ patterns, a year later
A field note on the questionnaires that landed this week — what's repeating from last April, what's new, and the two categories that are quietly eating the most response time.
Draft latency, a year on: 45s P95 to 28s
A year of draft-latency work. What moved P95 from 45 seconds to 28, which changes cost quality and which cost money, and the three tradeoffs we chose not to take.
Section 2: the technical approach without jargon buildup
Why almost every technical approach section opens with the wrong sentence, what the right opening looks like, and a rewritten example from a real bid. The jargon buildup that kills evaluator attention in the first paragraph.
Query understanding, a year on: where the model won
A year of hand-written query-rewrite rules versus LLM-based query rewriting on RFP questions. Which side won, where the hand-written rules still beat the model, and what the hybrid looks like now.
A year in public, what we'd do again
Three decisions that compounded over a year of building PursuitAgent in public, one we'd reverse, and one we're still uncertain about. Honest operator notes on what worked and what didn't.
State of Proposal Tools — Wave 2 2026
The second annual research drop. 45 vendors across four archetypes, updated capability matrices, pricing-pattern fractures, the grounded-AI taxonomy, and what changed vs. Wave 1 in August 2025.
The Saturday scope-creep kill list
A 10-minute Saturday drill. Four questions that retire a pursuit before it eats another sprint — so Monday's bid board reflects what your team can actually win.
The moat question, revisited
Opinion. A year in, where the durable advantage lives for a grounded-AI proposal product — and where it doesn't. Three candidate moats, two I believe in, one I don't.
Hallucination rate: a year-in measurement update
How we measure hallucination rate on grounded drafts, what the number looks like a year in, what moved it since the early baseline, and where the number lives in production for customers to see.
The compliance matrix revisited, one year in
What we wrote about compliance matrices in May 2025, what we've learned since, and the five corrections that change the recommendation. A one-year retrospective on a foundational RFP-mechanics piece.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.