The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Improve — make it easier to accept
+Before I publish this RFP to vendors, make it easy for procurement to score. Put the evaluation…
Improve — make it easier to accept
+Before I publish this RFP to vendors, make it easy for procurement to score. Put the evaluation criteria and the mandatory documents on page one, surface the top three disqualifiers at the top, make pricing submission a clearly labeled table, and flag anything that would make a bidder hesitate to respond.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+Procurement emailed asking me to add an indemnity clause that our finance director says could…
Decide — diagnose the stuck moment
+Procurement asked for a legal clause I don’t understand
Procurement emailed asking me to add an indemnity clause that our finance director says could expose the clinic to unlimited risk. I don’t have in-house counsel and the bidding deadline is nine days away. What is the likely trade-off here and what concrete wording change should I propose to keep bidders comfortable without increasing our exposure?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Over the last four procurements we’ve rewritten scope and scoring after proposals come in, costing…
Become — change the pattern
+We keep reworking RFPs after bids arrive
Over the last four procurements we’ve rewritten scope and scoring after proposals come in, costing time and damaging vendor trust. I want one change to our RFP drafting habit that stops scope creep and speeds award decisions. What recurring mistake are we making and what habit should we adopt to fix it?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Where the evidence lives
Who was seen doing this, and what people really ask.
Software tasks in the LLOS Work Atlas come from evidence, never a feature list: careers attested to do the work, real job descriptions, and the questions people actually ask (with their view counts). Facets — feature, workflow, troubleshoot, administer, deploy, scale — are open metadata: the work decides, not a taxonomy.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.