Blog · Page 19
Field notes.
Page 19 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
The 20-minute proposal retro
The ritual we run after every submit. Five questions. One owner per action item. Twenty minutes. Why most proposal post-mortems don't happen and what makes this one stick.
Procurement-side pain is real — and underserved
Buyers also hate the category. Three quotes from public procurement blogs and what they tell us about how the industry has under-served the buyer side of the RFP relationship.
The color-team review discipline, explained for modern teams
Pink, red, gold, white. The four-team review discipline most modern proposal shops know by name and don't actually run. This post reclaims it — what each team is for, why teams skip it, the rubrics, and how to run reviews async in 2025.
SME collaboration, Part 3 of 4: the 20-minute capture call
The synchronous meeting that saves four days of draft revision when the question is genuinely complex. The agenda template, the recording-and-transcript discipline, and what gets routed to a capture call vs. an async ticket.
The citation density target per section
Why executive summaries get two citations per paragraph and technical sections get five. The rationale for citation density as a section-level target, and what happens to drafts that fall below it.
Naming the category: proposal intelligence
Why we coined 'proposal intelligence' instead of riding the existing labels — RFP software, response management, content automation. What the phrase has to earn, and what we're explicitly not claiming with it.
Reviews watch: what G2 and Capterra said in September
Monthly aggregation of public review activity across the major proposal-management vendors. Four competitor deltas worth noting from September 2025.
The scoring rubric on the first read of any RFP
Three minutes. Find the scoring paragraph. Note the page, the heading, and the weights. The habit that shapes the entire response — and why most teams skip it.
The executive summary that fits on two pages, always
Length is a win-theme signal to evaluators. A two-page executive summary is a commitment; a six-page executive summary is a hedge. Six compression moves I run every time.
Numeric claim extraction and verification
How we parse numbers from drafts — percentages, dollar figures, head counts, dates — and check each one against a KB source before the sentence ships. The pipeline, the regex floor, the LLM ceiling, and what we still get wrong.
SME collaboration, Part 2 of 4: ticketed asks and response SLAs
Why 'just ping them on Slack' fails as an SME workflow, what a structured ticket form should contain, and the response SLAs that make the queue legible to engineering managers and proposal leads at the same time.
Cost control for RAG: daily budgets, fallback models, burn alerts
How we keep RAG spend predictable per tenant. Daily budgets, model-tier fallbacks, and burn-rate alerts before the bill spikes — with the dashboard and the rules.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.