Blog · Page 27
Field notes.
Page 27 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
DDQ Anatomy, Part 3 of 4: the security section
The security section is 60 questions long, mostly SOC 2-shaped, and it's where vendors most often ship answers that won't survive the buyer's actual security review. Here's what's asked and how to respond.
The APMP BOK 2025 update, decoded
The APMP Body of Knowledge is the closest thing the proposal profession has to a canonical text. Here's what it covers, how it has evolved, and where the 2025 update sits relative to the practice — based only on what's public.
Shipped: multi-doc RFP ingest with attachment dependencies
RFPs ship as bundles. The scoring rubric, the technical appendix, the pricing workbook. The Analyzer now ingests all of them as one pursuit, with dependencies tracked between them.
Three exec summaries I rewrote this week, part 2
Three illustrative before-and-after exec summary openings. The patterns that fail, the edits that work, and why the second sentence is where most exec summaries lose the reader.
The claim-level verification pass, explained
After the draft model writes a sentence, a smaller verifier model reads each substantive claim and asks: is this entailed by the source block? Here's how that works, what it costs, and where it still misses.
Legacy RFP UI is the moat — for the incumbents
Clunky enterprise software isn't a bug for the legacy RFP vendors. It's a switching cost. A founder's note on why the worst UX in B2B is also the most defensible — until something breaks the spell.
Our retrieval latency budget, explained
Where the milliseconds go in a single retrieval call: embedding lookup, vector search, reranker, hybrid merge, payload hydration. P50 120ms, P95 400ms, and what we cut to get there.
DDQ Anatomy, Part 2 of 4: legal and privacy
The legal and privacy section of a vendor DDQ is where 45 questions repeat bid-to-bid. Here's what they ask, what evaluators check, and how to answer without losing a week to it.
SAM.gov RFP volume, Q1 2025
What the federal procurement portal published in the first quarter of 2025. Public data only — directional signals on volume, agency mix, and category drift, with the SAM.gov citations to verify each claim.
Shipped: KB block freshness alerts in review
Stale KB content now flags itself before a reviewer touches it. The freshness signal sits inline on every drafted answer that cites a block past its refresh date.
The shadow SMEs who should be on every proposal invite
Three roles answer the hardest questions on most proposals and aren't titled as experts. How to identify them in your org and why they belong on the kickoff invite.
The DDQ response playbook, end to end
A canonical playbook for due-diligence questionnaires. Seven stages from intake to post-mortem write-back, what each stage owns, where each one breaks, and why the same DDQ next year should take half the time.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.