Skip to navigation

Ada CLI 1.11.0

This release adds commands that read and set the greeting and the closing of the AI Agent’s email replies, for each inbox and language. The commands show only on an Agent that sends each email reply as one email.

Changes

This section lists what the release adds or changes.

  • channels email inboxes lists the email inboxes and their IDs. For example: adacli <instance> channels email inboxes.
  • channels email show prints the greeting and the closing of an inbox for each language of the Agent. For example: adacli <instance> channels email show --inbox default.
  • channels email set-greeting sets the greeting for one language. Write {first_name} where the end user’s first name goes. An empty text sends no greeting, and --reset goes back to the default greeting. For example: adacli <instance> channels email set-greeting --language de --text "Guten Tag {first_name},".
  • channels email set-closing sets the closing for one language. An empty text signs the reply with the Agent’s name only, and --reset goes back to the default closing. For example: adacli <instance> channels email set-closing --language de --text "Mit freundlichen Grüßen,".

See Ada CLI.


Ada CLI 1.12.0

This release lets you set the pages that a web import leaves out.

Changes

This section lists what the release adds or changes.

  • knowledge scrape takes --exclude-paths <paths...> with --crawl. A path excludes that page and every page under it, and * matches any text. For example: adacli <instance> knowledge scrape --name "Docs" --urls https://example.com --crawl --exclude-paths /blog.
  • knowledge sources update <id> takes --exclude-paths <paths...> to replace the paths of a web import, and --clear-exclude-paths to remove them. A change applies from the next sync.
  • knowledge sources --json gives each source its exclude_paths.

See Ada CLI.


Metrics-driven improvement loop

Custom Metrics and the improvement loop are available on every account. Write a standard for your AI Agent in plain language, and Ada scores every conversation against it. Then one prompt starts a loop that finds why conversations fail, stages a fix, tests it, and rolls it out. The loop stops only to ask for your approval.

Repeat untilevery test passes You approve The metric showsif the fix worked 1. Write a metric 2. Measure 3. Find why 4. Find the fix 5. Test it 6. Roll out and track

Write your own metrics

A custom metric scores each conversation against a standard that you write.

  • Write a metric from a sentence: Describe the behavior in Generate from description, and the dashboard drafts the metric. A quality check finds wording that the judge can’t apply the same way on every conversation.
  • Read the results: Each conversation gets a verdict, with the judge’s reason and a quote. Each metric shows its pass rate over time, by channel, and by Intent.
  • Start with history: When you activate a metric, score up to 10,000 past conversations.
  • Ada standard metrics: Asks once and Acknowledges upset first score every AI Agent with no setup.

Improve with one prompt

The improvement loop turns a failing metric into a tested fix. The loop needs no setup of its own. An AI assistant gets the steps from the Ada MCP server, or from the ada-optimize skill with the Ada CLI.

To start the loop, give your AI assistant one prompt:

Improve the "<metric name>" metric. Use the Ada MCP tools.

To carry your date range and filters, copy the prompt from the metric on the Metrics page instead. The assistant then does these steps:

  1. Finds why: It reads the failing conversations and groups them by cause. First, it checks whether the metric or the judge changed on the day the pass rate moved.
  2. Finds the fix: It stages the smallest set of edits on a change set. Nothing changes on your live AI Agent.
  3. Tests it: It runs test cases in Simulations. If a test fails, it revises the fix and tests again, for up to 3 rounds.
  4. Rolls it out: It shows you simulated conversations, then recommends a live test or a promotion.

The assistant asks for your approval before it creates a test, before each test run, and before any rollout or promotion. After the rollout, the metric’s pass rate shows whether the fix worked.

Learn more about Custom Metrics and the improvement loop steps.


Exclude pages from a web import with the Knowledge API and the MCP server

The Knowledge API now reads and sets the pages that a web import leaves out. Every source response returns exclude_paths, and PATCH /v2/knowledge/sources/{id} accepts it. Send a list to replace the paths, or null or an empty list to remove them. A change applies from the next sync.

The MCP server’s edit_agent_config sets exclude_paths on a website import, and list_entities returns it at full detail.

The dashboard already has this setting. See Exclude pages from a web import and Web import.