← Real buildsWünscheCustomer care · case file

TST_Wunsche_Aftersales_Agent

Handles consumer aftersales email — repair, replacement, spare parts, user manuals, service-center delegation — by classifying with confidence, routing on warranty status and claim value, and either replying from code-held templates or preparing a full handoff for human review. — 10 tasks (10 completed) in the 30 days to 2026-08-10; 20 tasks in the 14 days to 2026-07-13 — live but low-volume; the docs' clearest named production CX case

In production50 nodes in the graph7 steps drawn
13 credits = $1.30 for a full logged run
measured · credit-rail measured
1
Look up case history in Airtable; parse the email, detect language, screen for escalation keywords
2
Identify sender type and retailer; query the product database (DAB)
3
Classify into a canonical category with confidence; extract product and customer facts
4
Route: repair/replacement by warranty status and claim value; spare parts; user-manual availability; non-service mail
5
Look up service-center and email-target contacts in Airtable
6
Assemble the reply — templates and signature held in code — or prepare the human-readable manual-review handoff
7
Create the case record in Airtable; send or reply; tag the mailbox

Where the money goes, per run

Step typeCountRateSubtotal
Code / integration steps39$0.025$0.975
Model calls · standard tier8$0.1$0.8
Model calls · mid tier2$0.2$0.4
Document parses1$0.2$0.2
Rate-card estimate, standard tier$2.38

Full graph at rate card: 39 code/integration x $0.025 = $0.975; 8 std x $0.10 = $0.80; 2 mid x $0.20 = $0.40; parse $0.20; total $2.38 ceiling. Costliest single lane: 39 nodes = 31 code ($0.775) + 5 std ($0.50) + 2 mid ($0.40) + parse ($0.20) = $1.88. Measured figure (the catalog's CX anchor, logged Aug 2026): 13 credits = $1.30 for a full run, ~3 credits ($0.30) on early exit, run on a mid-tier model (03-projects/27-cx/01-planning/overview.md '校准' section). Reconciliation: measured $1.30 sits below my $1.88 max-lane arithmetic because a real run does not touch every parallel side-write; against the $0.88 standard-tier menu ('aftersales + intake') the tier assumption that closes the gap is MID — the menu's own top-tier figure $2.68 implies $0.60 of standard-tier judgment ($2.68-$0.88 = 3x$0.60), so mid doubles it to a predicted $1.48 vs $1.30 measured (within ~12%, a run skipping 1-2 judgment steps). Caveat: in the 2026-08-28 snapshot only N4 Classification and N12 ResponseAssembly sit on GEMINI_3_1_PRO; the other 8 prompt nodes are Flash — so the measured mid-tier billing reflects run-time tier, not today's per-node preferredModel. Code 39 = 24 tool/code nodes (10 CodeExecutor, 3 Airtable formula lookups, 2 RecordCreate, 2 DAB QueryData, 3 Outlook tags, 2 MessageSend, 1 MessageReply, 1 S3) + 14 rule_based conditions + 1 inert no-tool execution node (empty objective).

Measured: 13 credits = $1.30 for a full logged run (~3 credits on early exit), measured August 2026 on a mid-tier model — documented as the 'CX aftersales full run' anchor; standard-tier menu equivalent is $0.88, so the gap is model tier (credit-rail measured)

Models seen in the graph: preferredModel: GEMINI_3_FLASH x33, GEMINI_3_1_PRO x2 (N4 Classification and N12 ResponseAssembly — N12's fallback chain is BEDROCK_CLAUDE_OPUS_4_7, GPT5_4); all 14 conditions rule_based (llmModel GEMINI_3_FLASH x6, GPT4_1_MINI x8)

Graph read: 04-agents/w-nsche/tst-wunsche-aftersales-agent/agent.json (50 nodes). Note: 04-agents/README.md marks w-nsche/ as superseded by wunsche/ (slug-normalization fix), but the TST production graph snapshot exists ONLY under w-nsche/ — the catalog's source path is correct.

What a copycat build should know

  • Classifier-router topology: N4 classifies into a canonical category with confidence on Gemini 3.1 Pro (the largest prompt in the CX fragment library), per-category route nodes N6-N10 (repair/replacement by warranty status and claim value, spare parts, user manual, non-service, SC delegation), then exactly two convergence nodes — N12 assembles every automated reply, N13 packages every manual-review handoff.
  • 10 CodeExecutor nodes hold the deterministic spine: Airtable formula builders, case-payload builders, DAB query builder + response handlers, subject tokenizer, and — critically — reply templates and the signature are held in code, so styling cannot drift with the model (27-cx overview calls this the most deterministic graph on the CX line; UNiDAYS has 0 code nodes).
  • All 14 conditions are rule_based, routing on flags set by upstream prompt nodes; intake N1 screens escalation keywords and applies a hard automated-notification veto (false positive = silently abandoning a customer) before anything else runs.
  • Lookups are three distinct Airtable tables (case history, service-center contacts, e-mail-target contacts) plus the DAB product database via custom QueryData API with code-built queries — the reply is grounded in records, and every outcome writes a case record back to Airtable before send/tag.

Lessons from the client record

  • The same graph bills 3x depending on model tier: $0.88 standard menu vs $1.30 measured mid vs $2.68 top — quote tier explicitly in any offer; also, the API totalCost field is credits/100, NOT dollars (27-cx/01-planning/overview.md, flagged as a known trap).
  • Full run vs early exit is a 4x cost spread (13 vs ~3 credits) — per-task averages are meaningless without the exit-mix.
  • This is the docs' clearest named production CX case, but volume is only 10 tasks/30d (20 in the prior 14-day window) — cite it as production wiring and pattern proof, not scale proof.
  • Workspace hygiene: read the graph from w-nsche/ even though the folder is marked superseded — the wunsche/ replacement folder never received the TST agent, and the DEP_/copy variants in the probe all show 0 tasks.

Reusable fragments cut from this agent

  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/01-intake-接件与解析.md#1
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/01-intake-接件与解析.md#2
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/01-intake-接件与解析.md#3
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/03-classify-定类与抽取.md#1
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/03-classify-定类与抽取.md#2
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/05-lookup-查库与取证.md#1
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/05-lookup-查库与取证.md#2
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/05-lookup-查库与取证.md#3
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/05-lookup-查库与取证.md#4
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/05-lookup-查库与取证.md#5
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/06-route-定路径与判定.md#1
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/06-route-定路径与判定.md#2
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/06-route-定路径与判定.md#3
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/07-compose-写回复.md#1
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/07-compose-写回复.md#2
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/07-compose-写回复.md#3
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/08-commit-写回与打标.md#1
  • cxWünsche 售后(生产) · 代码03-projects/27-cx/02-resources/run-steps/08-commit-写回与打标.md#2
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/09-handover-交人打包.md#1
  • cxWünsche 售后(生产) · 提示词03-projects/27-cx/02-resources/run-steps/09-handover-交人打包.md#2

What it is made of

AftersalesTechnical documentsMicrosoft OutlookAirtableproduct database (DAB) via custom queryS3

04-agents/w-nsche/tst-wunsche-aftersales-agent/agent.json · 04-agents/README.md · 04-agents/_probe/task_ranking_2026-08-10.json · 03-projects/27-cx/01-planning/overview.md · 03-projects/30-module-library/02-resources/menu-extract-corrections.md · 03-projects/alloyed-cx/04-outputs/production-cx-table-zh.md · 03-projects/27-cx/02-resources/run-steps/01-intake-接件与解析.md · /Users/zhichaoli/Documents/GitHub/solution-intelligence/content/agent-catalog.json