# Audit Your Operational Substrate: A Prompt Toolkit for Academic Founders **Faraz Rizvi** *Faraz Rizvi is a UK operator-practitioner writing about the work between a research breakthrough and a fundable company. He runs SpinUp Forge.* --- ## How to use this toolkit > **Note.** These kits are designed to help your thinking and focus. LLM outputs vary depending on the model, the inputs, and the context. Treat every output as a draft for your own review, not a finished deliverable. This is a set of prompts. You paste them into Claude, ChatGPT, or Codex CLI, you answer the agent's clarifying questions truthfully, and you read what comes back. The toolkit does two specific jobs. It surfaces the operational gaps in a one-to-three-person UK academic spinout in its first 18 months post-licence, and it produces a first concrete action per gap. It does not build the substrate for you. The substrate, as Piece 3 of this series sets out, is four layers of named workflows, knowledge, evaluation, and trust. The toolkit is the audit and first-action layer that sits in front of that work, so you can see what to build and in what order. The prompts assume you are early. They assume you are running on chat-plus-SaaS today, your board pack is assembled by hand, and nobody has yet written down a procedure for any of it. Calibrate accordingly if you are further along. Three voice rules apply throughout. The agent drafts, you ship; every output is a draft you review before any external use, which is why the review gate is named explicitly in each prompt. The agent's diagnostic only works on real context, so when it asks for clarifying detail you answer truthfully rather than aspirationally. And the prompts are conversational scaffolds, not magic; your judgement is what makes the outputs useful. A founder who pastes a prompt and accepts the output verbatim is doing chat-plus-SaaS dressed up in heavier vocabulary. A founder who pastes the prompt, reads the output critically, edits, and runs the procedure twice is starting to build a substrate. Once you have built the substrate, these prompts evolve from one-shot copy-paste into agent skills with persistent context and named tools. That is later. The toolkit is the on-ramp. --- ## The overall operational-gap audit The failure modes that end seed-stage spinouts in the first 18 months cluster predictably. Board pack inconsistency before the first institutional cheque. A financial model that cannot model the next round without a rebuild. Customer-discovery cycles that decay after the ICURe cohort closes. An IP register that drifts as invention disclosures, paper drafts, and contractor agreements accumulate. Hiring stalled at the role most needed because the JD does not exist yet. Investor update cadence that collapses by month four. Most founders I speak to recognise three of those six without prompting. The point of this first prompt is to name the cluster, walk you through your actual state on each, and produce a ranked diagnosis of which gap is hurting you most right now. You will get more from this prompt if you have your last board pack, your most recent financial model, and your last two investor updates open in another tab when you run it. The agent will ask for specifics. Answering "we send investor updates monthly" tells the agent nothing. Answering "we sent updates in months one, two, and three, missed month four, sent two paragraphs at midnight in month five, and have not sent month six" tells the agent everything. ``` You are an experienced UK seed-stage spinout operator. Your job is to audit my operational substrate gaps and produce a ranked diagnosis with one specific next action per gap. Context to assume: - I am a founder of a UK academic spinout, first 18 months post-licence. - Team is one to three people, mostly academic. - We run on chat-plus-SaaS today; no procedure is written down. Walk me through my current state on each of the six failure modes. Ask concrete questions until you have real evidence to rate severity. Do not accept generic answers, if I say "monthly", ask when the last instance was, who produced it, how long it took. The six failure modes: 1. Board pack inconsistency, last pack date; KPI definition continuity vs prior quarter; time to produce; cash bridge ties to which bank statement; risk register diff against prior pack. 2. Financial model that cannot model the next round, last rebuild vs roll-forward; can it answer "18-month plan to £6m Series A on three named hires" without rebuild; reproducible sensitivities. 3. Customer-discovery decay, interviews in last 30 days; where notes are stored; when synthesis was last updated; top three objections in writing right now. 4. IP register drift, patent families on licence; invention disclosures since licence; contractor assignment clauses; last TTO contact. 5. Hiring stalled, most overdue role; JD in writing yes/no; compensation band; interview rubric; time-to-JD. 6. Investor update cadence, updates in last six months and dates; named metrics covered; word count of most recent. When you have enough evidence per mode, produce: ## Operational-gap diagnosis For each gap, ranked most-severe to least: ### Gap N. [Name] - Severity: Critical / High / Medium / Low. One-sentence justification, quoting the founder-stated evidence that drove the rating. - Evidence: bullet list of the founder-stated facts justifying severity. - One specific next action this week: named precisely. Not "improve investor updates" but "draft an investor-update procedure with named inputs (KPI deltas, hiring status, IP diffs, customer notes) and a fixed send-date of the 5th of each month". You must not: fabricate evidence I did not give; assume I am more technical than stated; produce a diagnosis before asking enough questions; recommend tools or vendors; auto-execute anything. Review gate: the diagnosis is a draft. I review every gap, severity, and next action before treating any of it as accurate. If you are uncertain about a rating, say so. Begin by asking me about failure mode 1. ``` Read every severity rating against the answer you gave the agent and challenge any rating that does not feel grounded in what you actually said. The "next action" per gap is the most useful part of the output, because it converts an abstract gap into something you can do this week. Pick the top one or two gaps and run the per-workflow prompt below for whichever workflows address them. Do not try to fix all six at once. The honest founder reading the diagnosis will recognise that some of the gaps have been visible for months; the diagnosis is not new information, but naming the rank and the next action is the part that moves you. --- ## Workflow 1. Board pack assembly The board pack is the workflow that breaks first and shows fastest. A 2026 fund leading a Series A expects four quarters of consistent KPI definitions, a cash bridge that ties to last month's bank statement, and a risk register that diffs cleanly against the prior pack. Most seed-stage spinouts arrive having reinvented those documents three times in nine months, and the fund passes politely without explaining why. Good board-pack assembly is boring. It runs the same way every quarter, against the same input feeds, with the same review gate. The founder reads, flags two or three items that need judgement, signs the rest. This prompt produces the procedure that lets you assemble the pack that way. It is the worked exemplar of the toolkit, because the other five workflows follow the same shape. ``` You are an experienced UK seed-stage spinout operator. Your job is to help me write a procedure for board pack assembly that runs the same way every quarter, against named inputs, producing a named output, with a named review gate. Context to assume: - UK academic spinout, first 18 months post-licence, one to three people. - The pack goes to a seed-stage board (lead investor, founder, one NED). - No procedure is written down yet. Before drafting, ask me: 1. When was the last pack assembled and how long did it take? 2. What sources were used, bank app, accounting system, financial-model spreadsheet, CRM, customer notes, risk register, prior pack? 3. Did KPI definitions match the prior quarter? Where did they drift? 4. Did the cash bridge tie to a specific bank statement? Which one? 5. What cadence does the board expect, monthly, quarterly, ad hoc? 6. What does the board chair say they want and do not want to see? 7. What format, slides, narrative, both, and what typical length? 8. What needs founder judgement every time vs what is mechanical reconciliation? When you have my real answers, draft: ## Procedure: Board pack assembly ### Inputs Named, typed inputs. For each: name, source, producer, format, how the procedure receives it. Example: "KPI feed, source: financial-model spreadsheet, sheet 'KPIs', format: rows of {metric_name, current_quarter, prior_quarter, definition}, received by: paste from spreadsheet, or, once a knowledge layer exists, queried directly." ### Steps Numbered procedure steps. Each step names what is done, by whom or what, and the intermediate output. Mechanical and judgement steps flagged separately. The procedure runs the same way every quarter. ### Outputs Named outputs. For each: name, format, recipient, send-date convention. ### Review gate Named. Who reviews what before it leaves the building, what they look for, what they may skip, what they must read line by line. ### Eval checks At least one check that catches regressions. For board pack: KPI definitions reconcile to the prior pack (list any drift); cash bridge ties to the most recent month-end bank statement to the penny; risk register diffs cleanly against prior pack with each added, removed, or changed item explained in one sentence. Each check must be verifiable deterministically by a human or a second agent run. ### Failure modes this procedure protects against One paragraph naming the specific failure modes, e.g. KPI drift between quarters, cash bridge not tying to bank, risk register accumulating resolved items. You must not: fabricate inputs or outputs I did not name; assume the procedure runs without a founder in the loop (the founder reviews and signs every pack); recommend a specific tool or vendor; write the procedure to run without a human in the loop. Review gate (for this prompt's output): the procedure is a draft. I will run it once manually before treating it as standing procedure, then edit, then run it a second time before relying on it. Flag any assumption you are uncertain about. Begin by asking me question 1. ``` The output is a procedure, not a board pack. Run the procedure once, manually, for the next pack you would have assembled anyway. Notice where the procedure as written breaks against the real inputs. Edit the procedure, not the pack. Run it a second time on the following pack. The eval checks at the foot are the part you will be tempted to skip, and they are the part that protects you against a board pack that looked right but reconciled wrong. Keep them. --- ## Workflow 2. Investor update The monthly investor update is the cadence object. It is the single artefact that tells a lead investor, every month, that the team does what it says, on the date it said. When the cadence collapses, the trust signal degrades for a reason that has nothing to do with the science. The good investor update is short, named-metric-led, plain-prose, and lands on the same date each month. This prompt produces the procedure that lets you produce one in a defined window of founder time. The agent is not writing the update for you in this toolkit; it is writing the procedure. ``` You are an experienced UK seed-stage spinout operator. Help me write a procedure for the monthly investor update, same way every month, same send-date, named output the lead investor can read in two minutes. Context to assume: UK academic spinout, first 18 months post-licence, one to three people, four to ten recipients, no procedure written down. Ask me first: 1. How many updates in the last six months and on what dates? 2. What named metrics did each cover? 3. Word count and format of the most recent? 4. Input sources, KPIs, customer interviews, hiring, IP, runway? 5. What does the lead investor say they want and do not want? 6. Preferred send-date convention? Then draft the procedure in the standard format: Inputs, Steps, Outputs, Review gate, Eval checks, Failure modes this procedure protects against. Eval checks must include: named-metric coverage check; word count check; plain-prose register check (no marketing vocabulary, no autonomy claims, no number without source). You must not: fabricate metric history; assume tone I have not stated; draft the update content itself (you are drafting the procedure, not the update); recommend tools. Review gate: the procedure is a draft. I run it once on the next update manually before relying on it. Begin by asking me question 1. ``` The output is a procedure that defines what an update is, what it contains, when it ships, and what gets reviewed before it leaves. By month three, the procedure becomes the standing template and the founder time spent per update drops from a half-day to a defined window. The named-metric coverage check is the eval that matters most, because it catches the slow drift where each update covers fewer metrics than the last until what ships is two paragraphs that say nothing. --- ## Workflow 3. Financial-model maintenance The financial model that closed the seed back-solves from the number the founders wanted. It is correct as a fundraising artefact and useless as an operating one. The model that runs the company is rolled forward, not rebuilt; it pulls actuals from the bank feed and updates assumptions explicitly; it can answer "what does an 18-month plan to the next round on three named hires look like" without a rebuild from scratch. This prompt produces the procedure for maintaining the model in that state. It does not build the model. It builds the maintenance discipline. ``` You are an experienced UK seed-stage spinout operator with a finance background. Help me write a procedure for financial-model maintenance, rolled forward, not rebuilt, able to model the next round on named assumptions. Context to assume: UK academic spinout, first 18 months post-licence, one to three people, model in Excel or Google Sheets, founder is not a finance professional. Ask me first: 1. When was the model last meaningfully updated and what changed? 2. Does it close the round on paper, and on what assumptions? 3. Can it answer "18 months on three named hires and £6m Series A in month 14" without a rebuild? 4. Where do actuals come from, accounting system, bank app, both? 5. Where do assumption changes get recorded, in the model, separate doc, nobody's head? 6. How often are sensitivities reproduced from current assumptions? Then draft the procedure in the standard format. Eval checks must include: actuals reconcile to most recent bank statement; closes-the-round-on-paper test runs against current assumptions; sensitivities named in the last board pack reproduce from current model state. You must not: rebuild the model; assume a finance background I have not claimed; recommend specific finance vendors; propose the procedure execute without human review of the rolled-forward output. Review gate: the founder reviews every monthly roll-forward before relying on the model for any external conversation. Begin by asking me question 1. ``` The output is a maintenance procedure, not a model. The first time you run it you will find at least one assumption that has not been documented anywhere except in your head; write it into the model where the procedure asks for it. The eval check that earns its keep is the closes-the-round-on-paper test against current assumptions, because it forces the model to remain a usable artefact rather than a frozen snapshot of the seed raise. --- ## Workflow 4. Customer-discovery synthesis Post-ICURe, a strong cohort finishes with forty interviews and a write-up. Six months later, the rhythm has settled at two interviews a month and the synthesis is the ICURe document, untouched. When a lead investor asks what the team has learned in ninety days, "we have been heads-down on technical milestones" is the wrong answer. The good customer-discovery practice in a seed-stage spinout maintains a rolling synthesis updated weekly or fortnightly, with named segments, named objections, named willingness-to-pay signals, and every claim traceable to an interview identifier. This prompt produces the procedure that holds that discipline together. ``` You are an experienced UK seed-stage spinout operator who has run customer discovery for science-led companies. Help me write a procedure for rolling customer-discovery synthesis. Context to assume: UK academic spinout, first 18 months post-licence, one to three people; interviews recorded via Otter, Read.ai, or raw notes; team did ICURe or equivalent pre-licence. Ask me first: 1. Interviews in the last 30 days and where notes are stored? 2. When was the synthesis last meaningfully updated? 3. Named segments I am running discovery against? 4. Top three customer objections in writing right now? 5. Willingness-to-pay signals on record, and where? 6. Format of the synthesis, doc, table, slide, mix? Then draft the procedure in the standard format. Eval checks must include: every claim in the synthesis traces to an interview identifier; segment list is consistent with segments named in the last board pack; objections list sorted by frequency and recency. You must not: fabricate interviews; assume objections I did not state; propose the agent runs interviews; recommend specific transcription vendors. Review gate: the founder reviews every synthesis update before any external use, and is responsible for the traceability of every claim. Begin by asking me question 1. ``` The output is a synthesis procedure that names how interviews flow in, how they get tagged to segments, how the rolling document gets updated, and what the eval check looks like. The traceability eval is the one that protects you in diligence; an investor reading the synthesis can ask "which interview produced this objection" and you can answer in ten seconds. Run the procedure on the next batch of interviews and notice where the segments named in the procedure no longer match the segments showing up in the interviews. That mismatch is the most useful signal the procedure produces in its first month. --- ## Workflow 5. IP register The licence schedule lists three patent families. By month ten there is a fourth invention disclosure the TTO has not seen, a paper draft mentioning a fifth, a contractor agreement silent on assignment, and a postdoc who joined two months ago whose IP assignment paperwork is in someone's inbox. Nothing malicious. Nobody owns the register and it drifts. The good IP register in a seed-stage spinout is a single live document with assignment status per item, diffed monthly against the TTO contact log, with named owners for each entry. This prompt produces the procedure that holds the register live without requiring a patent lawyer in-house. ``` You are an experienced UK seed-stage spinout operator with TTO and IP exposure. Help me write a procedure for maintaining a live IP register. Context to assume: UK academic spinout, first 18 months post-licence, one to three people; licence schedule lists patent families and may include know-how or copyright; team continues to invent, publish, and contract for work. Ask me first: 1. Patent families on the licence schedule? 2. Invention disclosures since licence, and any filed? 3. Papers drafted or submitted since licence describing patentable matter? 4. Contractor agreements explicit on assignment, and who reviews them? 5. When did the TTO last receive an updated register from us? 6. Any third-party background-IP items relevant to the company? Then draft the procedure in the standard format. Eval checks must include: every register entry has an owner, assignment status, and date last reviewed; monthly diff against the TTO contact log produces no unexplained gaps; contractor and employee records reconcile to the register on the assignment column. You must not: provide legal advice; assume facts about background IP I did not state; recommend a specific patent attorney or IP-management vendor; propose the agent files or corresponds with the IPO directly. Review gate: the IP register is reviewed by the founder and shared with the TTO before any external IP conversation. Begin by asking me question 1. ``` The output is a procedure for keeping the register live, not a legal document and not a substitute for counsel. The eval check on contractor and employee assignment is the one that prevents the silent failure where work done in month seven turns out not to belong to the company. Run the procedure monthly with the TTO contact looped in. The first run will surface at least one item that has been drifting for longer than you realised. That is the procedure earning its keep. --- ## Workflow 6. Hiring pipeline The founder knows they need a head of commercial and an MLE. Six months pass. No JD. No compensation band. No interview rubric. A warm-intro candidate takes another offer because the founder cannot articulate the role in writing within forty-eight hours. The good hiring discipline in a seed-stage spinout maintains JD drafts on demand, candidates and interview notes in one place, rubric scores recorded against named criteria, and a time-to-JD from "we need this role" to "JD is live" measured in days, not months. This prompt produces the procedure for that. ``` You are an experienced UK seed-stage spinout operator who has hired into small science-led teams. Help me write a procedure for the hiring pipeline. Context to assume: UK academic spinout, first 18 months post-licence, one to three people; first non-academic hires typically commercial, MLE, or operations; founder is not a recruiter. Ask me first: 1. Most overdue role and how long it has been open in my head? 2. JD in writing, and when last edited? 3. Compensation band, and how it was set? 4. Interview rubric, and what it scores against? 5. Candidates spoken to about this role, and where notes live? 6. Time-to-JD from "we need this role" to "JD is live"? Then draft the procedure in the standard format. Eval checks must include: every open role has a JD in writing; every JD has a named compensation band and an interview rubric; time-to-JD is measured and reported for every new role; candidate notes stored in one place and traceable to rubric scores. You must not: recommend specific ATS vendors; assume compensation benchmarks I did not state; draft candidate-facing outreach in this prompt (that is a separate workflow); propose the agent runs interviews. Review gate: the founder reviews every JD and every rubric before external use. Begin by asking me question 1. ``` The output is a hiring procedure that keeps the pipeline alive between roles. The eval check on time-to-JD is the one to watch; if it slips above forty-eight hours for the second role you open, the procedure is not yet standing on its own and needs another pass. The procedure does not solve the harder problem of finding the right person, but it does solve the easier problem of being ready when the right person appears. --- ## The prioritisation prompt You have six workflows in front of you. You cannot build six at once and you should not try. The right prioritisation depends on round stage, runway, board cadence, current FTE, what you are most behind on, and what conversation is coming next. A spinout three months from a Series A pre-emption conversation needs board pack and financial model first. A spinout that just closed seed and is two interviews a month behind on customer discovery needs customer-discovery synthesis first. A spinout where the lead investor has noticed two missed monthly updates needs investor update first, irrespective of what else is wrong. The prioritisation prompt takes your situation as input and produces a build sequence and rough effort estimate for the first one or two workflows. ``` You are an experienced UK seed-stage spinout operator. Take my current situation and produce a ranked recommendation of which one or two workflows to build first, with a build sequence and rough effort estimate per workflow. Context to assume: I have completed the gap audit or have a clear sense of my top two gaps; I am one to three people, first 18 months post-licence. Ask me first: 1. Round stage, post-seed, raising bridge, pre-Series-A? 2. Runway in months on current burn? 3. Board cadence, monthly, quarterly, ad hoc? 4. Current FTE and who does what? 5. What I am most behind on right now, in my own words? 6. Next investor conversation coming, and when? 7. Founder time per week available for codification work? Then produce: ## Build sequence ### First workflow to build: [Name] - Why this one first: one paragraph grounded in my stated situation, naming the specific risk this workflow addresses and the specific conversation it protects against. - Rough effort estimate: range in founder-hours to reach standing procedure that runs the same way twice, typically 4 to 12 hours spread over two to three weeks, with conditions named. - First concrete step this week: a single named action. ### Second workflow to build (only if first is stable): [Name] - Same structure. - Trigger to start: the specific signal that means the first workflow is stable enough to start the second, e.g. "first workflow has run twice with the same procedure and the eval checks have passed both times". You must not: recommend more than two workflows; fabricate runway or round-stage detail; assume founder time I did not state; recommend a vendor or tool. Review gate: the build sequence is a draft. The founder decides whether to proceed, defer, or sequence differently based on judgement the agent does not have access to. Begin by asking me question 1. ``` The output is a sequencing recommendation, not a commitment. Read the "why this one first" paragraph and check whether the reasoning matches your sense of the next investor conversation that is coming. If it does not, push back on the agent in the same conversation; tell it the specific thing it has wrong and ask for a revised recommendation. The two-workflow ceiling is deliberate. A founding team that builds two workflows to standing-procedure quality in the first quarter is ahead of one that starts six and finishes none. --- ## What to do once you have run the toolkit Build one procedure. Run it twice. Evaluate against the eval checks the procedure itself produced. Iterate. That is the discipline the toolkit is designed to put in place, and it is the discipline that compounds. The temptation will be to run all the prompts in one sitting, generate six procedures, and treat the resulting stack as a substrate. It is not a substrate. Six untested procedures are six aspirational documents. One procedure that has run twice and passed its own eval checks twice is the start of a substrate. The tooling follows the procedure. Once the procedure is in writing, the question of which model, which orchestrator, which knowledge layer becomes tractable in a way it was not before. Piece 3 of this series describes what the standing substrate looks like once the procedures are in place. Pieces 1 and 2 describe the funding architecture and the agentic bottleneck that make this work load-bearing in 2026 rather than optional. The toolkit is the on-ramp. The codification act itself is the thing that matters; the tooling is downstream of it. The same founding team can run a larger company than the headcount admits to. That is not a slogan, it is the consequence of writing down what you used to keep in your head, running it twice, and noticing it now runs without you. --- ## Related reading - [Piece 0: There Has Never Been a Better Time to Be an Academic Founder.](/thinking/spinout-honesty-introduction.html), series introduction. - [Piece 1: The UK Spent £58 Billion on Research.](/thinking/funding-system-changed-its-question.html), the funding system. - [Piece 2: The Bottleneck Has Moved.](/thinking/bottleneck-is-not-the-model.html), the agentic bottleneck. - [Piece 3: Chat Plus SaaS Is No Longer Enough.](/thinking/operator-substrate-first-18-months.html), the operational substrate this toolkit is the on-ramp to. ### Companion kits - [Rate-of-change self-locator](/toolkit/rate-of-change-self-locator/index.html), paired with Piece 0; the entry-point selector for the series. - [Funnel-position diagnostic](/toolkit/funnel-position-diagnostic/index.html), paired with Piece 1; the funding-pipeline diagnostic. - [Thesis-distinction confirmation](/toolkit/thesis-distinction-confirmation/index.html), paired with Piece 2; the two-workflow identifier. This toolkit is the operational on-ramp to the argument the series makes. The series makes the case that the work has changed; the toolkit is the first concrete step a founder can take in response.