---
title: How to Show the Board What an AI Agent Did (2026)
description: Count sessions, handoffs, writes denied, and one wrong answer. At 50,000 sessions the published AgentCore silhouette is about $791 a month — a bill to plan, not money saved. We are not publishing a containment rate.
url: https://www.factualminds.com/blog/how-to-show-the-board-what-an-ai-agent-did-2026/
datePublished: 2026-09-22T00:00:00.000Z
dateModified: 2026-09-22T00:00:00.000Z
author: palaniappan-p
category: AI Agents
tags: ai-agents, ecommerce, operations
---

# How to Show the Board What an AI Agent Did (2026)

> Count sessions, handoffs, writes denied, and one wrong answer. At 50,000 sessions the published AgentCore silhouette is about $791 a month — a bill to plan, not money saved. We are not publishing a containment rate.

[McKinsey's State of AI 2025](https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai) put **23%** of organizations at scaling agents in at least one function, and **62%** at least experimenting. A board that funded the experiment will ask what it did. A transcript and a vendor containment score do not answer that. A weekly pack does: sessions, handoffs, writes denied, one wrong answer, and what the platform actually cost.

This is part 6 of **AI Agents for Business**. The pre-build ranking is [How to Evaluate AI Agent Opportunities](/blog/how-to-evaluate-ai-agent-opportunities-2026/). The field-guide scoring write-up is [AI Agent ROI](/blog/ai-agent-roi-ecommerce-automation-priority-2026/).

**The job.** Give the board a record of what the agent looked up, what it refused, and what it cost — not a story that it "handled" the queue.

**This week.** Fill one row from traces you already have. If you have no traces, you are not ready for this pack. You are ready for the [ten-ticket test](/blog/ten-tickets-before-an-ai-agent-talks-to-customers-2026/).

**A person still signs.** Anything that moves money. The pack reports that those writes were denied or handed off. It does not celebrate a silent refund.

**Skip it** when the loop is not live, when no one owns the handoff queue, or when leadership will only accept a tickets-down percentage. We are not publishing one.

> **Copy the pack** — Blank rows and the figures you must not paste as your result: [`agent-weekly-board-pack.md`](https://www.factualminds.com/examples/architecture-blog-2026/ecommerce-ai-agents-series/agent-weekly-board-pack.md). Price your volume on the [AgentCore pricing calculator](/tools/amazon-bedrock-agentcore-pricing-calculator/).

FactualMinds is an AWS Select Tier Services Partner. We have **no published AI-agent case study**. The pack is a worksheet. Your counts stay yours.

**Our take:** report handoffs and denied writes before you report a containment rate. The board will want the rate. You will not have an honest one until the traces exist. Ship the traces.

## The five lines

| Line | What it is | What it is not |
| --- | --- | --- |
| Sessions | Turns the host ran | A chatbot vendor's conversation count with no tool log |
| Handoffs | Stops that opened the human queue, with a session id | A low number you hope means the bot was smart |
| Writes denied | Policy blocks on refund, cancel, purchase order, quote issue, price, or credit release | Zero, when the write tool was never attached |
| One wrong answer | The worst turn: tool result versus what the model said | A green dashboard |
| Platform cost | Your invoice line for the host plus the model | **~$791/mo** relabeled as savings |

Support-style AgentCore at **50,000 sessions a month is about $791 a month** in platform plus model. That figure is from our [AgentCore vs Amazon Q decision guide](/blog/aws-bedrock-agentcore-vs-amazon-q-enterprise-decision-guide-2026/). If you are not at 50,000 sessions, do not quote it as your bill. It is a floor to plan against, the same way the ROI note already says.

## Figures that are not your KPI

Gorgias, via [Redo](https://redo.com/resources/articles/order-editing/what-is-wismo), puts where-is-my-order at **about 18%** of tickets. That tells you the slice is common. It does not tell the board your agent closed 18% of anything.

Gateway server-side tools cut median tool round-trip **~180 ms to ~95 ms** on a B2B CRM assistant (12 tools, about 8,000 turns a day). That is a platform canary. Your order system will be slower. Do not put the canary in the board pack as store latency.

## What to use instead

- **Before go-live.** The [readiness score](/blog/ecommerce-ai-agent-readiness-assessment-2026/). Under **16 out of 30**, do not discuss writes with the board at all.
- **Choosing the first workflow.** [Evaluate opportunities](/blog/how-to-evaluate-ai-agent-opportunities-2026/). That score is not this pack.
- **You need a build note.** The field guide for the family you actually shipped, starting at [15 automations](/blog/ai-agents-for-ecommerce-15-automations-2026/).

## If you only do one thing

Print last week's traces. Count handoffs and denied writes. Attach one wrong answer. Put the invoice next to them. If you cannot do those four, do not invent a containment percentage for the board.

## For your technical lead

**On June 17, 2026**, AgentCore Harness reached general availability ([What's New](https://aws.amazon.com/about-aws/whats-new/2026/06/amazon-bedrock-agentcore-harness-generally-available/)). **Agents Classic** is in maintenance for new customers after **July 30, 2026**. The pack still needs a session id and a tool trace. A Classic bot with no trace cannot fill the row.

> **What broke** — A steering deck that treated the **~$791/mo** silhouette as money saved, because the unit cost of a purchase order looked large. Feasibility was low. The team still wanted the write. The ROI note already records that failure: impact is not feasibility, and the silhouette is a **cost floor**, not savings. Detection: the deck's "savings" line had no invoice beside it. Recovery: report the invoice. Rank the workflow again with the veto on.

## What to do this week

1. Name the agent family and the human who owns handoffs.
2. Export one week of session ids. If the export does not exist, stop. You are pre-launch.
3. Count handoffs and policy denies. If no write tool is attached, write "no write tool" — not zero.
4. Pick the worst wrong answer. Quote the tool result and the model text.
5. Put your host-plus-model cost on the same page. Compare to **~$791/mo** only if you are near **50,000** sessions. Otherwise use the [calculator](/tools/amazon-bedrock-agentcore-pricing-calculator/).
6. Do not paste **18%**, **62%**, or **23%** into the "our result" cell.

## What this post doesn't cover

It does not score which workflow to staff first. It does not retell the human-in-the-loop design. It does not publish a containment rate, a tickets-down percentage, or a client board deck. **23%**, **62%**, **~$791/mo**, **~18%**, and **~180→95 ms** are figures we already published, reused here so the pack has a scale — not so you can claim them.

**Primary next step:** [AI Agents](/ai-agents/).

## FAQ

### When should you NOT take an agent number to the board?
Skip the pack when the agent is not live, when you cannot name the human who owns handoffs, or when the only figure anyone will accept is a tickets-down percentage we have not measured. A demo transcript is not an operating result.

### What could go wrong if we report the $791 figure as savings?
That silhouette is support-style AgentCore platform plus model at about 50,000 sessions a month. It is a cost to plan against. Calling it money saved tells the board the invoice is a benefit. Model your own volume on the pricing calculator.

### What could go wrong if containment is the only KPI?
A bot that never hands off scores well and answers wrong. Count handoffs and writes the policy denied. If a write tool was never attached, say that. Do not print zero denies as proof of safety.

### Can we paste the public 18% where-is-my-order share as our result?
No. Gorgias, via Redo, puts where-is-my-order at about 18% of incoming requests. That is an industry mix, not your containment rate. Your pack uses your ticket ids and your traces.

### Is this the same as the ROI score we used before we built?
No. The ROI note ranks which workflow to staff first. This note is what you count after a turn has run. Do not reuse the pre-build score as a weekly result.

---

*Source: https://www.factualminds.com/blog/how-to-show-the-board-what-an-ai-agent-did-2026/*