Skip to content

Slack Adds Built-In AI Coding Agent for In-Channel Requests

Short answer

Salesforce announced Slack Code, an agentic coding feature built into Slack that lets users request code changes, scripts, or integration fixes directly in a channel and have an AI agent draft, test, and propose the change. For ops and support teams, this shortens the path from 'we need a small fix' to a working pull request.

What this means for operators

Most 10-200 person B2B companies don't have engineers sitting in every support or ops thread — a broken webhook, a misfiring Zapier step, or a report that needs one more filter usually waits in a backlog. Slack Code puts a coding agent where the request already happens: the Slack channel where support flagged the bug or ops asked for a tweak. If it works as described, a support lead can type the problem in plain language, get a proposed fix or script back in the same thread, and route it to a human reviewer before merging — no separate ticket, no context lost translating the issue to a developer. The catch is governance: someone still needs to review and approve what the agent proposes before it touches production systems, and access controls over which repos or workflows the agent can reach will matter more than the convenience.

Salesforce has introduced Slack Code, a feature that brings an agentic AI coding assistant directly into Slack channels, according to Salesforce News. The tool is designed to let users describe a coding problem or automation request in a Slack conversation and have an AI agent draft a solution — potentially a script, a bug fix, or a workflow change — without leaving the chat interface.

The announcement frames this as reducing friction between the people who spot operational problems (support agents, ops staff, sales operations) and the engineers who traditionally fix them. Exact details on which models power the agent, pricing, and rollout timeline were not specified in the available announcement and should be treated as unconfirmed pending Salesforce's full documentation.

For small and mid-sized B2B companies, the relevant shift isn't the coding capability itself — plenty of AI coding tools exist — it's the placement. Slack is already the record of where operational problems get reported and discussed. An agent that can act on that record without requiring a handoff to a separate tool removes one of the more common delays in ops workflows: translating a plain-language complaint into a ticket, then into a task, then into code.

Companies running lean support or ops teams without dedicated engineering headcount stand to gain the most, provided review and permission controls are configured carefully before any agent-proposed change reaches a live system. Companies that already route every fix through a formal engineering queue may see less immediate benefit, since the bottleneck there is process, not tooling.

As with any agent that can generate and potentially merge code, the operational question is less "can it write the fix" and more "who signs off before it ships." Teams adopting this should treat the initial rollout as a pilot: instrument what the agent proposes, require human approval on anything touching production, and log its output the same way any new integration would be logged in security or SOC2 review documentation.

Source: Salesforce News

Next step

Visibility Analyzer

This is what the Visibility Analyzer measures on a real site: which answers cite you, which pages an engine cannot retrieve, and what to fix first. Free to run.

Run a free visibility audit

Free to run. No card.

Fee
Free
Length
One run, minutes

Free tier: two analyses a day, no card required.