Capturing undocumented work
Turn a walkthrough recording into a usable SOP without asking the expert to write it up.
— Operations & Process
Extracts ordered steps with role and system from a process walkthrough transcript and rewrites them as a complete SOP with exceptions and quality checks.
2–3 hours → ~5 minutes
For one document, brief or record at a time
No coding required
— USE CASES
Turn a walkthrough recording into a usable SOP without asking the expert to write it up.
Document what a leaver actually does while they are still there to describe it.
Record the process in each location and compare the resulting SOPs for real differences.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
Findings on the end-to-end process are written up as a document that reads like professional output, with each claim tied back to a process step.
Each process step is assessed against explicit criteria you control, so the same standard is applied across the end-to-end process on every run.
Facts and fields are lifted out of process documentation and run data and held in a consistent shape, process step by process step.
The run works from process documentation and run data you supply, so conclusions about the end-to-end process are anchored to your evidence rather than general model knowledge.
The fastest way to document a process is to have someone talk through it. In practice it shows up as capturing undocumented work: turn a walkthrough recording into a usable SOP without asking the expert to write it up. It is the kind of work that decides whether a recommendation survives scrutiny — and the kind that quietly eats 2–3 hours of senior time whenever it comes round.
Skillsize turns that work into a Skill: you supply the material, and what comes back is a complete SOP: purpose, scope, roles, numbered procedure, with exceptions and quality checks captured explicitly. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. The practical effect: 2–3 hours of manual work becomes a ~5 minutes run, held to an identical standard on the tenth engagement as on the first.
SOP generator from transcript exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Identifies where adoption of a new system, process or way of working stalls after go-live, with an evidence-backed report on barriers, workarounds and differences between functions.
Assesses AI readiness through anonymous staff evidence, identifying where AI can improve day-to-day work and the practical barriers that could prevent those gains.
Maps how an organisation actually operates using anonymous accounts from its people, producing an evidence-backed diagnostic of responsibilities, decisions, handoffs and duplicated effort.
Reads a set of weekly status notes for progress, blockers and RAG, charts the trend, and writes an executive digest focused on trajectory.
Reviews a proposed change against your change policy and returns a governed advisory decision — approve, approve with conditions, defer to the change board or reject — weighing risk, blast radius and rollback, with a change manager sign-off required before anything reaches production.
Assesses a refund or compensation request against the contract terms and refund policy that govern it, then returns a decision on approving it in full, in part, offering a goodwill gesture or declining, with every element of the remedy traced to the clause that allows it and anything beyond an agent's authority routed for review.