Blog · Page 5
Field notes.
Page 5 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
The Saturday review of outgoing pursuits
A 15-minute Saturday ritual for reviewing the week's outgoing proposal pursuits. Three questions, applied in order: what to kill, what to push, what to staff up. The cheapest pipeline discipline we run.
Three exec summaries I rewrote this week, part 11
Part 11 of the monthly series. Three real executive summaries, anonymized, rewritten. What was wrong in the original, what changed in the rewrite, and what each one taught about the shape of the RFP it responded to.
Our infra spend for proposal workloads, year one
Database, inference, storage, and ops. What we spent running proposal workloads over our first year, broken down by category. Where the cost curves went where we expected, and where they surprised us.
A grid for past-performance writeups
The table that turns 20 disorganized references into submit-ready past-performance prose. Four rows, six columns, and the discipline that makes every reference tell the same story from the buyer's angle.
RAG for past-performance reference selection
How the retriever picks the three best past-performance references out of 180 for a given scope. Not cosine similarity on a paragraph — structured retrieval over multiple facets with a scorer that knows what a good reference looks like.
DDQs from non-US buyers are shaped differently
A field note on three field-level differences between US, UK/EU, and APAC DDQs. Different privacy regimes, different data-residency framings, different evidence conventions. Small shifts that bite if you answer them on autopilot.
The defense RFP cycle: March patterns
A teardown of DoD small-business contracting patterns in March across the last three fiscal years. Where the peaks are, what triggers them, and what the shape of March 2026 suggests about FY Q2 volume.
Shipped: bulk RFP ingest with duplicate detection
A short changelog entry. Bulk ingest of 10 RFPs in a minute, with block-level duplicate detection so the same clauses across multiple RFPs don't double-count in your KB.
The federal March pipeline looks like this
A short field note on what our own federal-opportunity stream surfaced this week. Three clusters, one surprise, and what it tells us about the FY Q2 surge.
The claim-verification cost profile, stage by stage
Per-claim verification is the defense against citation hallucination. It also costs real money. A breakdown of token costs at each stage of the verification pipeline, with the numbers we actually see in production.
Section 1: the executive summary nuances most teams miss
The executive summary is the section most teams write last, worst, and most generically. When you write it depends on the RFP's shape. Three shapes, three rules, and the nuances nobody tells you.
Reviewer feedback routing: comment to block to KB
How we close the loop from an inline comment on a draft paragraph to a versioned edit on the KB block that generated it. The routing is boring; the discipline it enforces is the whole game.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.