Free playbook · 15 guides
Getting a model to write a good reply is the easy part. This playbook covers the rest: the helpdesk events, permissions, knowledge, tools, tests and on-call work that make an AI support agent safe to put in front of customers, and keep it improving after launch.
Vendor-neutral, practical and free. No sign-up.
The work you don't see
A customer asks where their order is. Before the agent replies, all of these have to go right, and each one is a decision you'll make while building. Follow a step to the guide that covers it.
Select the approved configuration and check whether the agent owns the conversation.
Guide 04: CheckUse current account data and relevant policy. Ask for a missing detail when required.
Guide 07: FindUse a bounded task and permitted tools. Check any action result.
Guide 09: Act or answerRecheck the latest message and human ownership. Send once, then confirm delivery.
Guide 03: Deliver15 guides in the order you'll need them. Each one opens with a short answer, works through a fictional shop's real support case, then lists the build decisions, the checks that prove each one, and the work it needs after launch.
Guides 01–09
Scope, running cost, helpdesk events, conversation state, identity, knowledge, retrieval, behavior and tools: everything a first answer depends on.
Guides 10–15
The console, security, testing, measurement, launch and improvement work that keeps the agent useful after day one.
A good answer to a simple question is table stakes. These everyday failures are where home-built agents usually go wrong, and the playbook shows how to handle each one.
The model bill rarely decides it: engineering time, QA, maintenance and the months before launch do. Put in your own numbers to compare an in-house agent with My AskAI.
Why 10 LLM calls? Each reply runs query rewriting, retrieval reranking, groundedness checks, and answer validation. It's why our raw cost per reply is ~3–4× a naive build's — and why the resolution gap exists.
My AskAI pricing mirrors the calculator at myaskai.com/pricing: Pro $199/mo (~1,000 tickets included), Scale $499/mo (~2,000 included), Enterprise from $999/mo with negotiated volume rates. Pricing is per reply ($0.06 on Pro, $0.05 on Scale/Enterprise); email tickets bill one extra reply, and AI tags or tasks/tools/images are add-ons. For an exact quote use the pricing page and paste it into the override field.
$142,212
over 12 months, compared with building it yourself — including the build cost and the resolution-rate gap
$95,202
$30,000 of engineering + $65,202 of savings missed during the 2-month build, when you could already be live on My AskAI.
69% resolution
just to break even versus My AskAI (at 75%).
Days vs 2 months
My AskAI deploys in days; the build answers nothing until v1 ships.
| Humans only | My AskAI | Self-build | |
|---|---|---|---|
| Monthly tickets | 30,000 | 30,000 | 30,000 |
| AI resolution rate | — | 75% | 60% |
| Tickets resolved by AI | 0 | 22,500 | 18,000 |
| AI software / LLM cost | $0 | $4,899 | $600 |
| Engineering upkeep | $0 | $0 | $1,500 |
| Tickets still needing humans | 30,000 | 7,500 | 12,000 |
| Cost per human-handled ticket | $1.67 | $1.67 | $1.67 |
| Human support cost | $50,000 | $12,500 | $20,000 |
| Total monthly cost | $50,000 | $17,399 | $22,100 |
| Monthly savings vs humans only | — | $32,601 | $27,900 |
On top of this, the self-build needs 2 months and $30,000 of engineering before it answers its first ticket — My AskAI goes live in days. The headline number above includes both.
None of this is priced into the numbers above.
Everything the guides reference, in one place. All examples use synthetic data.
25 checks to pass before customers depend on the agent.
Daily, weekly, monthly and per-release work, with owners and the evidence to keep.
30 files: Python examples, tool schemas, test cases, runbooks and records.
A demo that answers from a help center can take days. A version you can trust with real customers takes much longer, because most of the work is in helpdesk delivery, permissions, testing, recovery and the people who run it after launch, not the model call. Build a thin end-to-end version for one support case first, then estimate the rest from the gaps it exposes.
Build when support automation is part of your product and you can staff engineering, QA and on-call for it for years. Buy when you want the result inside your helpdesk without that ongoing work. The Build vs Buy calculator on this page compares the two with your own ticket volume and costs.
Usually not to start. A direct model SDK, one durable worker, your existing database and a clear control flow cover most first versions. Add a framework or another agent only when it removes a real problem you can measure, such as state recovery or tracing.
No. The guides describe generic responsibilities, not My AskAI internals, and list several provider options for each component. Where My AskAI offers a part ready-made, a short note at the end of the guide says so.
No. The examples are short teaching files with synthetic data that run locally and make no network calls. They show one pattern each (webhook signatures, access checks, response filtering, metric arithmetic) and state their limits. They are not a complete agent.
Engineers building or evaluating an in-house AI support agent, and support leaders who need to know what a safe launch looks like and what the team will have to keep doing afterwards.
My AskAI is an AI support agent that already does all of this inside Zendesk, Intercom, Freshdesk, Gorgias and HubSpot. Set it up in minutes and pay per AI reply: $0.05 on the Scale plan, with models, hosting and maintenance included.
