Blog · Page 23
Field notes.
Page 23 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
Reviews watch: what G2 and Capterra said in July
Monthly aggregation of competitor review deltas and our own. What changed in July's review feeds across Loopio, Responsive, Qvidian, AutogenAI, and us.
The AutogenAI teardown: UK-origin RFP AI, two years in
What's public about AutogenAI: UK origin, generation-heavy stack, where they win in EU procurement, where the citation discipline is thin, and what we learned reading their materials.
Three exec summaries I rewrote this week, part 4
Continuing the series. Three before/after exec-summary passages from this week's bids, including a tabled structure that scored well in a state-government pursuit.
Retrieval over diagrams, not just text
How we index D2 code and diagram descriptions so an architecture question can ground to a specific figure. The pipeline, the failure modes, and the citation surface for a diagram source.
Good win themes are verbs, not adjectives
Adjective win themes — robust, scalable, frictionless — fail the swap test. Verb win themes describe what changes for the buyer. Three before/after rewrites of real proposal language.
The answer provenance graph in the KB
Every block in the knowledge base tracks source, author, approver, and last-used-in. The provenance graph isn't bookkeeping — it's a product surface. Here's what it stores and what it powers.
Why we don't do autonomous proposal agents yet
An opinion piece. What an agentic drafting system would have to guarantee that retrieval doesn't, why we don't think the category is ready, and the work we'd want to see before changing our position.
Proposal win rates by sector, Q1 2025
A public-data synthesis of proposal win rates across healthcare, SaaS, defense, and state/local procurement for Q1 2025 — what's measurable, what isn't, and where the sector cuts diverge.
Shipped: answer-block inheritance across projects
When you edit an approved KB block, in-flight proposals inherit the change without overwriting their local edits. Here's how the merge resolves and what we did about the conflict cases.
Q1 — what we got wrong in ninety days
Ninety days into the public phase of the company. Five specific things we got wrong, what we changed, and what is still open. Written in the same spirit as the launch post — if I cannot say it on the blog, the discipline is theater.
The reranker that paid for itself
Rerankers add latency and cost. They earn it back when retrieval is borderline and the wrong block in the top-K poisons the draft. Where we run a reranker, where we do not, and the honest tradeoffs.
Past performance that actually maps to the scope
Selecting which prior contracts to cite is a craft skill, not a database query. Three worked examples of past-performance selection — what to cite, what to omit, why the relevance map matters more than the impressive number.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.