Task statement 4.3 · Workflow integration and solution design

4.3 · Supporting Solution Design

In Wrenfield Housing, the course example, the operations team has its requirements for the repairs-request redesign and a pilot plan for the Millbrook estate. Now it must build the solution: a guide that call handlers use to sort each incoming repair request. If the team takes Claude's first idea, drafts it once and never tests it on real requests, a tenant with black mould can wait in the routine queue.

Why it's tested

The tempting request is "write us a triage guide", followed by rolling out whatever comes back, because the draft looks finished. Claude then offers one plausible design, so the choice is made before anyone compares options. The draft has also never met a real request. The opposite mistake is to plan something the team cannot build, such as a rule inside the repairs system. That work needs code or a system connection, so it goes to the developers as a written requirement.

KnowledgeThree stages, and who decides at each

Here a solution is a process and its working materials, such as a triage guide, a template or a checklist, not software. Solution design is choosing the approach: Claude proposes several options and states the trade-off of each, meaning what you give up to get its benefit. Development is making the materials, which Claude drafts and the team checks. Iteration is improving them after real use: the team tests them on real cases, collects what failed, and Claude helps revise. At every stage Claude proposes and drafts, while the team chooses, tests and owns the result. This rules out adopting Claude's first proposal untested, and any answer in which the team builds an integration itself.

  1. Give the requirements: paste what the solution must do and the limits it must respect.
  2. Ask for options: several different approaches, each checked against every requirement, with what each one gives up.
  3. Choose, and split off: pick the option that meets the requirements; send anything needing code or a system connection to developers.
  4. Develop the materials: have Claude draft them in a form the team can edit and share.
  5. Iterate on real cases: test the materials on real work, collect every failure with the right answer, revise, and test again.

Interactive · building the triage guide, stage by stage

Four stages of building the triage guide, from top to bottom. On the left is what the team asks Claude for or does at each stage; on the right is what comes back. Design compares three options against three requirements, and the team chooses the decision guide and sends automatic tagging to IT as a requirement. Develop drafts guide version 1 with a pilot log template. Test runs the first pilot week on 96 requests and finds 9 sorted wrongly, labelled failures. Revise fixes the guide from those 9 cases, and week two shows 2 of 104 wrong. A stage not reached yet is dashed and labelled not reached yet. THE TEAM, WITH CLAUDE WHAT COMES BACK 1 · Design 3 options, each checked against the 3 requirements DECIDES Decision guide chosen auto-tagging → IT as a written requirement 2 · Develop Draft the guide and a pilot log template NOT REACHED YET PRODUCES Guide v1 · 3 steps urgent · damp and mould · routine NOTHING YET 3 · Test Pilot week 1, Millbrook: 96 real requests NOT REACHED YET SHOWS FAILURES · 9 of 96 wrong 6 damp and mould → routine 3 dripping taps → urgent NOTHING YET 4 · Revise Paste the 9 cases, change only what each cause needs NOT REACHED YET PRODUCES Guide v2, tested again week 2: 2 of 104 wrong, both added to the test set NOTHING YET Stages 3 and 4 repeat each pilot week until the guide meets the requirements.

Step through the four stages and see what each one hands to the next.

Design: the team picks the decision guide and sends automatic tagging to IT.

Develop: Claude drafts guide version 1 and a pilot log; the operations lead approves them.

Test: the pilot log shows which requests the guide sorted wrongly. Those failures feed the next stage.

Revise: one change per cause of failure, then the guide meets real requests again.

Dashed and labelled NOT REACHED YET: a stage still to come. The amber box labelled FAILURES holds the cases the next stage fixes.

KnowledgeDesign: options against the requirements

Claude should see the requirements before it proposes anything, because an option can only be judged against what the solution must do. Anthropic's guide to comparing options says to tell Claude what matters for your decision and to ask what you give up by not choosing the others. One proposal leaves nothing to compare. Wrenfield's team pasted the guide's three requirements, drawn from 4.1 and 4.2. Call handlers, who have no surveying training, sort every request when it arrives. No damp and mould request is ever sorted as routine. The method works from the pilot's first day without a new IT system. The categories were urgent (attend within 24 hours), damp and mould, and routine. Claude returned three options:

Decision guide

A one-page flow of three steps that staff work through in order.

Gives upSpeed: staff ask each step's question. Meets all three requirements, so the team chose it.

Keyword checklist

Staff tick words such as "leak" or "mould" that appear in the request.

Gives upEvery request that never uses the word, so damp can land in routine. Fails the second requirement.

Automatic tagging

The repairs system tags each online request by category before staff see it.

Gives upThe pilot start: it needs a change to the repairs system. Fails the third requirement, so it goes to IT.

The third option was worth keeping, but not for Wrenfield's staff to build. The operations lead asked Claude to draft a hand-over brief, a short written requirement that says what is needed and why and leaves how to the developers, then checked it and sent it to IT:

# requirement for the IT team (drafted with Claude)
Need: tag each new repair request as urgent, damp and mould, or routine.
Why: the pilot sorts by hand; online requests could arrive already sorted.
Must: never tag a damp and mould request as routine; staff can change any tag.
Test: the pilot requests, with the categories the surveyor confirmed.

SkillWorked example: development, then the first revision

For development, Claude drafted the guide as an artifact, the document Claude builds beside the chat for content that will be edited and shared (2.6). Version 1 had three steps. Step 1: is there danger now, such as no heating or hot water, water coming in, or a door that will not lock? Then it is urgent. Step 2: does the tenant mention damp or mould? Then it is damp and mould. Step 3: otherwise, routine. Claude also drafted a pilot log with three columns: request reference, category given, and category the surveyor confirmed. The operations lead adjusted lines with "Edit with Claude", then exported version 1 to Word. After the first pilot week on Millbrook, the log showed 9 of 96 requests sorted wrongly, and the first revision request was vague:

# revision request, before
The guide got some requests wrong in the pilot. Make it more accurate.
→ two pages, five new steps, nothing about the actual misses
# revision request, after
These 9 requests were sorted wrongly in week 1 (request text only, no names
or addresses), each with the category given and the one confirmed.
Group them by cause. Change only the steps a group shows are wrong.
Keep the guide to one page and keep everything else as it is.
→ step 2 adds tenants' words: black marks, musty smell, windows always wet
→ step 1 now asks: is water coming through a ceiling or near electrics?

The bad round lacked evidence: "more accurate" told Claude that something failed but not what, so it guessed and made the guide longer. The real failures had two causes. Six damp and mould requests went to routine because tenants wrote "black marks behind the wardrobe" or "windows always wet" and never used the words damp or mould. Three dripping taps went to urgent because staff read "leak" as water coming in. The pasted cases, without names or addresses as Wrenfield's AI policy requires, showed Claude what to fix, and the "keep" line left the rest unchanged, as in 1.3's one-change loop. Anthropic's testing advice is to mirror the real work, edge cases included. In week two, version 2 sorted 104 requests with 2 wrong, and both joined the test set.

Ask one question: can the team build and run this part with the Claude apps and its own documents? Yes → ask Claude for options against the requirements, draft the materials, and revise them from real failed cases. No → write the requirement with Claude's help and escalate it to a developer or architect.
Takeaway
  • In design, ask for several options and the trade-off of each against your requirements; Claude proposes, and the team chooses.
  • Iterate from evidence: collect the real cases the materials got wrong, with the right answer, and revise only what those cases show.
  • A hand-over brief to developers says what is needed and why, and leaves how to them.

check yourself

0 / 3 answered

A facilities coordinator at a university needs a new way to settle room-booking clashes. The agreed requirements: front-desk staff decide within one working day, and no new software this term. Asked "What's the best way to handle booking clashes?", Claude returned one detailed proposal built on a booking-system plug-in. The coordinator has seen no other approach.What is the most effective next prompt?

Select one.

A customer service lead built a checklist with Claude that sorts incoming complaints into billing, delivery and product quality. Over the first two weeks, 128 of 140 complaints were sorted correctly. The lead's review found 12 sorted wrongly, most of them refund requests for damaged goods filed under billing.Which TWO actions most directly improve the checklist?

Select two.

An HR officer designed a new-starter onboarding checklist with Claude. One option Claude proposed would create staff accounts automatically in the HR system when a contract is signed. The HR director wants that option eventually, but the checklist must start next month. The officer writes no code, and the IT team takes requests in writing.Which approach best gets onboarding started while preserving the automatic option?

Select one.

sources

  1. Claude Academy (Anthropic), "Compare and analyze competing options": tell Claude what matters for your decision; ask for what you are giving up by not choosing the others, alongside a recommendation. Checked 2026-10-15.
  2. Claude Help Center, "What are artifacts and how do I use them?": an artifact opens beside the conversation; it is made for content that is significant, self-contained and likely to be edited or reused; edit by asking Claude or with "Edit with Claude"; documents export to Word, PDF, Markdown and Google Docs; available on all plans, with code execution and file creation turned on. Checked 2026-10-15.
  3. Claude Platform Docs, "Define success criteria and build evaluations": design tests that mirror your real-world task distribution, and do not forget edge cases. Checked 2026-10-15.
  4. Wrenfield's triage guide, its three options, the IT requirement and the Millbrook pilot weeks are this course's example.