Blog · Page 9
Field notes.
Page 9 of 31. Browse the archive of RFP workflows, grounded-AI architecture, and proposal operations notes.
Federal spending cycles, 2025 to 2026
Continuing resolutions, shutdowns, reopenings. How the federal fiscal calendar actually shapes RFP cadence, and what proposal functions that touch federal work should plan for through mid-2026.
In preview: proposal templates v2 with custom sections
Template inheritance replaces copy. Sections defined once, customized per tenant, updated in one place. In preview behind the templates feature flag while the marketed Proposal Builder surface catches up.
The capture-to-proposal handoff checklist
Seven fields the capture team has to deliver before the proposal team starts writing. Why most handoffs fail on three of them, and how to enforce the handoff as a gate rather than a courtesy.
Migrating to Gemini Embedding v3, the safe way
A dual-index backfill and a staged cutover across two weeks. How we evaluated retrieval deltas before the switch, what we watched for during the cutover, and the one metric that gated the final flip.
The RFP kickoff, the 30-minute version
For small teams where a 90-minute Shipley kickoff is a non-starter. The trimmed agenda, what gets kept, what gets pushed to async, and the one artifact the kickoff still has to produce.
Caching the draft step
How we cache partial drafts across proposals without introducing stale-answer risk. The cache key design, invalidation rules, and the directional cost impact we measured internally.
RFIs and RFPs are distinct work
Why treating an RFI like an early draft of an RFP response loses the relationship. RFIs are informational for the buyer, not a preview of evaluation. Respond to them as such.
Reviews watch: what G2 and Capterra said in January
Monthly sweep of public review activity on Loopio, Responsive, QorusDocs, and Upland Qvidian. Q4 fallout shows up in January — renewal cycles, budget cuts, product regressions flagged in the wild.
The January past-performance backfill ritual
Two hours in mid-January to refresh last year's past-performance references so they actually carry the weight they need to for this year's bids. The shortlist, the edits, the re-approvals.
How we're talking about PursuitAgent this quarter
A messaging refresh done in public. The four short lines we kept, the ones we dropped, the new framing around grounded retrieval as a contract, and the reasons for each change. Written at the end of the annual-planning cycle.
Retrieval over Slack history: what works, what's too sharp
An experiment with RAG over customer-Slack channel history. Three useful retrieval patterns, two failure modes that led us to gate the feature behind explicit capture flags, and the operational guardrails.
Hiring a proposal manager in 2026: what actually changed
The job description template we use, the interview questions that still work, and the three things that have changed since 2024 about what a proposal manager role actually requires. Written for hiring managers staffing up in Q1.
Prefer to see the product?
Take the 5-minute tour, or start a trial workspace and see PursuitAgent draft answers with citations.