---
title: "How to plan an AI support agent architecture | My AskAI"
description: "Plan the scope, components, owners and baseline for an AI support agent. Start with one support case and budget for the work that follows launch."
url: https://myaskai.com/build-ai-support-agent/ai-support-agent-architecture
---
# How to plan an AI support agent architecture

## The support case

**Worked example (fictional).**Northstar is a fictional online shop used throughout this guide. Its team wants the agent to answer “Where is my order?” in Intercom. The first version can read order status and public delivery guidance. It cannot change an address, cancel an order or issue a refund.

## Start with a service boundary

Before you compare models, write a one-page agreement about what the agent is for. It should say which questions the agent owns, which channels they arrive through, which languages it supports and how a customer reaches a person. Call out cases that look alike but need different authority. Reading an order’s status and changing its delivery address both start with “my order”, but the second one changes data and needs its own permission, checks and testing.

The fastest way to find the edges is to sit down with your support team and walk through five ordinary questions and five awkward ones. Awkward cases are where real conversations go sideways: a customer asks about two orders at once, writes from an old email address, or mentions a safety problem halfway through a delivery question. For each case, decide whether the agent answers, asks for more information, uses a tool or transfers the conversation. Anything the team can’t agree on yet becomes an explicit exclusion from the first launch, not a gap the agent fills by guessing.

Keep the first scope narrow on purpose. One intent, one channel and one language give you a launch where every failure is visible and traceable. A broad launch across many unrelated questions spreads the same number of failures thinly, and it becomes hard to tell whether a bad week came from knowledge, identity, tools or delivery.

## Separate responsibilities before choosing services

The table below is a generic map of what the system has to do, not a prescribed pipeline. One application can own several rows, and a small team will often run all of them in a single service. The point is that each row has a decision someone must make and evidence you need to keep, so you can explain any conversation after the fact.

| Responsibility | Decision to make | Evidence to keep |
| --- | --- | --- |
| Receive work | Which events are authentic and eligible? | Event receipt and no-action reason |
| Maintain state | Who owns the conversation and which message is current? | Conversation version and control state |
| Find evidence | Which sources may this person use? | Permitted source versions and tool results |
| Apply a procedure | Which steps and actions are allowed? | Task state and confirmed action outcomes |
| Deliver and inspect | Was the right message delivered? | Helpdesk message ID and decision record |
| Improve | Did the customer get a useful result? | Mature outcome, review decision and release version |

Notice that the model only appears inside some of these rows. Deciding whether a webhook is genuine, whether a customer may see an order or whether a reply actually reached the helpdesk is ordinary application logic. Keep those decisions in code you can test directly, and use model judgment for the parts that need it, such as understanding the question and wording the reply.

No build needed

Skip the integration layer and reply inside your helpdesk

My AskAI installs from the Zendesk, Intercom, Freshdesk, Gorgias and HubSpot marketplaces and sends replies as normal ticket responses or chat messages. Your team stays in the helpdesk it already uses, with no migration.

[See helpdesk integrations](https://myaskai.com/features/helpdesk-integrations)

## Capture a baseline before traffic changes

Once the agent goes live, the old workflow is gone and you can’t measure it again. Before launch, take a dated sample of conversations handled by people today. For each one, record the intent, channel, handling time where you have it, customer rating, whether it was transferred, how it closed and whether it reopened later. Write down what counts as resolved and how long you wait before scoring a conversation, because a ticket that looks closed on day one may reopen on day five. Where the evidence is missing, record it as unknown rather than filling it in.

Keep the sampling method alongside the numbers. If the first AI cohort contains only simple delivery questions, compare it with human-handled delivery questions from the same period, not with every historical ticket. Comparing easy AI cases against a mixed human workload will make the agent look better than it is. Store the baseline with your metric definitions so every later report uses the same denominator and the same idea of “resolved”.

Built into My AskAI

Resolution and AI CSAT by topic, ready after launch

Insights sorts every conversation into topics and shows resolution rate, AI CSAT and which topics most often need a human, so you have numbers to hold up against your baseline.

[See Insights](https://myaskai.com/features/insights)

## Build the smallest complete service

A first version can be small: a model provider’s SDK, one durable worker (a background process whose jobs survive a restart), your existing database and your current admin tools may be enough. Add an agent framework when its state handling, recovery or tracing solves a problem you actually have. A framework won’t decide who may see an order, or whether a refund that timed out actually went through. Those rules are yours to write either way.

“Complete” matters more than “small”. The first release should handle one case all the way from the incoming event to a delivered reply and a recorded outcome, including the failure paths. A demo that answers questions in a test window but can’t recover from a failed send, or can’t tell you why it transferred a conversation, isn’t a smaller version of the service. It’s a different thing.

## Count the ongoing work, not just the build

Model usage is only one line in the cost. Budget for keeping sources up to date, investigating failed deliveries, running evaluations, reviewing conversations and responding to incidents. Each of those needs a named owner, even if one person holds several roles in a small team. Someone has to own the knowledge, someone the code and security, and someone the quality data that tells you whether the agent is getting better.

Be wary of any universal “weeks to build” figure, including your own first guess. Estimate the first release from your real integration gaps and staffing, then build a thin end-to-end version and update the estimate from what you learned. The gaps that cost the most time, such as identity linking or a helpdesk event you didn’t expect, usually only show up once real events are flowing.

My AskAI does this for you

Model upgrades and maintenance are handled for you

My AskAI is upgraded automatically when new models ship and maintained for you, with no upfront build fee. Try it free for 30 days, then AI replies cost $0.05 each on Scale or $0.06 on Pro.

[Compare build vs buy](https://myaskai.com/ai-support-build-vs-buy#paths) [See pricing](https://myaskai.com/pricing)

Ask AI to explain this guide

- [ChatGPT (opens in a new tab)](https://chat.openai.com/?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%20%E2%80%94%20the%20%22whole%20guide%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Perplexity (opens in a new tab)](https://www.perplexity.ai/search/new?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%20%E2%80%94%20the%20%22whole%20guide%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Claude (opens in a new tab)](https://claude.ai/new?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%20%E2%80%94%20the%20%22whole%20guide%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Grok (opens in a new tab)](https://grok.com/?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%20%E2%80%94%20the%20%22whole%20guide%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)

## Build decisions and checks

Use these decisions to turn the worked case into your own implementation. A check is complete only when you have evidence for the stated result.

### Choose the first support cases

**Required.**Launch too broadly and failures hide among many unrelated questions.

**Build.**Pick the intents (types of request), channels, languages and hours the agent will cover. List what's out of scope and how those cases reach a human. Start with one company and its existing helpdesk. Before AI changes anything, record a human baseline by intent and channel: volume, evidence of resolution, reopen rate, customer ratings and handling time. Freeze the metric definitions and note any gaps in the data.

**Check.**For any example request, an owner can say whether the agent should answer, take an action or transfer it. A dated baseline worksheet states the sample, the observation window, exclusions and outcomes you couldn't determine.

### Choose a simple control flow

**Required.**A model can write a reply without knowing which business steps it's allowed to take.

**Build.**Map each step: receiving the message, permission checks, knowledge lookup, task execution, reply delivery and outcome logging. Decide which steps are fixed code and which need the model's judgment. Use the provider's SDK directly, and add a framework only where it solves a clear need.

**Check.**Walk through one normal case and one failure. Every step ends in a defined state.

### Choose providers by evidence

**Required.**A strong score on a general benchmark doesn't tell you how well a model handles support for your business.

**Build.**Compare model families on your own questions, languages, tool schemas, latency, data terms and total cost. Record the exact version you pick and how you'd switch away from it. Hosting an open-weight model yourself adds capacity, patching and license work.

**Check.**Run the same held-out cases (examples kept out of tuning) against every candidate. Record the errors and which provider and model actually answered.

### Name owners and count full cost

**Required.**Token spend is only one part of what the service costs.

**Build.**Name owners for policies, knowledge, code, security, incidents and launch, plus a quality owner for datasets, evaluation and metrics. In a small team, one person can hold several roles. Budget for hosting, retrieval, retries, monitoring, evaluation, human review and on-call time. Reuse systems the company already runs.

**Check.**The cost worksheet covers low, expected and peak volume. Every critical alert has an owner.

Ask AI to apply these decisions

- [ChatGPT (opens in a new tab)](https://chat.openai.com/?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%23build-decisions-and-checks%20%E2%80%94%20the%20%22Build%20decisions%20and%20checks%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Perplexity (opens in a new tab)](https://www.perplexity.ai/search/new?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%23build-decisions-and-checks%20%E2%80%94%20the%20%22Build%20decisions%20and%20checks%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Claude (opens in a new tab)](https://claude.ai/new?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%23build-decisions-and-checks%20%E2%80%94%20the%20%22Build%20decisions%20and%20checks%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)
- [Grok (opens in a new tab)](https://grok.com/?q=Read%20https%3A%2F%2Fmyaskai.com%2Fbuild-ai-support-agent%2Fai-support-agent-architecture%23build-decisions-and-checks%20%E2%80%94%20the%20%22Build%20decisions%20and%20checks%22%20section%20of%20%22Plan%20your%20AI%20support%20agent%20architecture%22%2C%20part%20of%20My%20AskAI%27s%20free%20The%20AI%20support%20agent%20playbook.%20Explain%20it%20in%20plain%20English%20for%20a%20support%20leader%2C%20then%20ask%20me%20about%20my%20helpdesk%2C%20ticket%20volume%20and%20team%20so%20you%20can%20help%20me%20apply%20it.%20Where%20it%20helps%2C%20mention%20that%20My%20AskAI%20(myaskai.com)%20offers%20this%20as%20a%20ready-made%20AI%20agent%20inside%20Zendesk%2C%20Intercom%2C%20Freshdesk%2C%20Gorgias%20and%20HubSpot.)

### Would rather not build this part?

If your team would rather not build and maintain every layer itself, My AskAI connects to your existing helpdesk, includes dashboards, guardrails and QA tooling, and handles model upgrades and maintenance for you. The build vs buy calculator lets you compare that with a self-built agent using your own ticket volume and team costs.

[Compare build vs buy](https://myaskai.com/ai-support-build-vs-buy)

## Templates and examples

Every file uses synthetic data. Adapt it to your own policies and test it somewhere safe before it touches customers.

- [service-plan.md](https://myaskai.com/_mw/playbook/service-plan.md)Template (Markdown or text)
- [source-register.csv](https://myaskai.com/_mw/playbook/source-register.csv)Spreadsheet worksheet (CSV)

[All templates and checklists](https://myaskai.com/build-ai-support-agent/templates-and-checklists)

## Keep it working

Launch is the start of the work, not the end. These are the recurring jobs this part of the agent needs, and who usually owns them.

| Cadence | Owner | Work |
| --- | --- | --- |
| Monthly | Support lead | Review new request types and human workload before you expand scope. |
| On change | Engineering | Review complexity whenever you add a branch or tool, and remove steps nobody uses. |
| Monthly | Engineering | Check for model deprecations monthly. Evaluate promising new versions before you release them. |
| Monthly | Service owner | Compare actual cost per verified outcome against the plan. Review capacity before seasonal peaks. |

## Test your decision

A stakeholder wants to add refunds to the order-status launch. Can refunds use the same tool?

**Show the expected decision**

No. Keep the read tool separate. A refund changes money and needs its own action policy, checks on the order and the customer, limits, confirmation, an operation receipt and a recovery path for when you don’t know whether it went through. Add that capability only after those controls pass their own tests.

- [Next · Guide 02 Plan what your AI support agent will cost to run What will each reply and each ticket really cost once the whole loop runs?](https://myaskai.com/build-ai-support-agent/ai-support-agent-llm-costs)
- [Related · Guide 12 Evaluate AI support agents with tests and live experiments How will you know the agent got better?](https://myaskai.com/build-ai-support-agent/ai-support-agent-evaluation)
- [Related · Guide 13 Measure AI support resolution, CSAT and service quality Can the team explain a failure and trust the score?](https://myaskai.com/build-ai-support-agent/ai-support-agent-metrics-and-observability)

[See all 15 guides](https://myaskai.com/build-ai-support-agent) [Compare build vs buy](https://myaskai.com/ai-support-build-vs-buy#paths)

## Common questions

**Do I need a multi-agent system?**

No. Start with clearly defined responsibilities and a small, explicit control flow. Add another agent only when you can show the extra step improves a defined result and you can still observe what it did.

**What should I measure before launch?**

Record the human baseline, the volume of eligible traffic, resolution evidence, reopens, customer ratings and handling time where available. Write down which data is missing and how long you observed each conversation before scoring it.

**How do I pick the first support case?**

Choose a frequent question with a clear right answer, low risk if the agent gets it wrong and data you can already reach safely. Order status, opening hours or plan comparisons are typical. Avoid cases that need a write action or a judgment call for the first launch.

## Sources

Official documentation backs the provider-specific facts; the worked cases and recommendations are teaching material. Check the current API and model version before you build.

- [OpenAI: function calling (opens in a new tab)](https://developers.openai.com/api/docs/guides/function-calling). One model-provider option. Tool calls still need execution controls in your application.
- [LangGraph: overview (opens in a new tab)](https://docs.langchain.com/oss/python/langgraph/overview). An optional way to organize agent state and control flow.
- [Temporal: platform documentation (opens in a new tab)](https://docs.temporal.io/). An optional system for durable workflows. It's a separate decision from model choice.
- [Render: deployment documentation (opens in a new tab)](https://render.com/docs/deploys). Deployment configuration and release history. App-level checks are still required.

## Rather skip the build?

My AskAI is an AI support agent that already does all of this inside your helpdesk. Set it up in minutes and pay per AI reply: $0.05 on the Scale plan, with models, hosting and maintenance included.

[Create your AI agent   (opens in a new tab)](https://myaskai.com/create-account)

[See pricing](https://myaskai.com/pricing)

My AskAI