Blog · Page 14
Field notes.
Page 14 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
Discriminator vs. feature: which one moves the score
Two real RFP sections, same underlying win theme, different framings. Which framing evaluators picked, and the rule I extracted from comparing them.
The async drafting worker pool, explained
How 40 concurrent draft sections get written without saturating the LLM budget or crashing the rate limiter. The worker pool, the budget enforcer, and the retry ladder.
Thanksgiving week: how we staff three active pursuits
Our ten-minute Monday huddle that keeps the short week from collapsing. Three active pursuits, three owners, one rule about Wednesday at noon.
An anonymized winning proposal, torn down
A public-sector award with public artifacts. What won, what the scoring rubric rewarded, and three things a typical proposal team would have gotten wrong.
In preview: the post-mortem pipeline at submit close
The moment a proposal marks won or lost, PursuitAgent opens a structured post-mortem against the captured pair. In preview while the post-mortem template, reflection, and write-back loop mature toward general availability.
The proposal post-mortem template: preview
A Wednesday teaser for next week's pillar. The fields that matter in a post-mortem template, and the one section most teams skip.
Multi-tenant DDQ templates across customer accounts
How one SOC 2 answer shape generalizes across many customer tenants without leaking tenant-specific facts. The separation between template structure and tenant content, explained.
Past-performance library hygiene for year-end
Three questions that decide whether a past-performance entry stays in the library, gets rewritten, or gets retired. A December sweep that pays off in the Q1 pursuit wave.
Tuning pgvector HNSW for proposal workloads
M, ef_construction, ef_search — the three knobs that decide retrieval latency and recall in a pgvector HNSW index. What we chose for PursuitAgent and why.
The rolling Q4 capacity plan for proposal teams
A five-week look-ahead that reallocates the proposal team twice. Why a static quarterly plan breaks in Q4, and what a rolling version does instead.
Reviews watch: what G2 and Capterra said in November
The monthly aggregation of public reviews for proposal-management and RFP-automation tools. Q4 competitor deltas, new reviewers, and what customers are praising and complaining about this month.
The DDQ wave: what the inbox looks like this week
Mid-November volume snapshot across our own fleet. Volume, topic distribution, and the two categories growing fastest this week compared to the baseline.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.