LaunchDarkly Flag Change Watchdog with Hermes
Flag activity is bursty. A quiet fortnight costs almost nothing and a release afternoon fires two dozen entries, most of which are dropped after a single read because they are not flag changes. Hermes is built on open Hermes models and takes your apps as tools, which keeps a watchdog you leave on permanently from being priced like a reasoning job.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
checkout-v2-rollout
Percentage rollout moved from 25% to 100% of all contexts. Targeting rules and variations unchanged. Comment left on the change: green in staging all week, taking it to everyone before the weekend freeze.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect LaunchDarkly
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Flag policy
Which flag changes you want to hear about and which are routine - the environments you protect, your kill switches and permanent flags, and what makes a change risky enough that a named person should confirm it.
Runs on Hermes
Preselected for this page — connect your Hermes account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why Hermes for this agent
Dropped entries finish early
Anything that is not a flag change ends the run after one read. On an account with heavy audit traffic, most runs are exactly that short.
Open weights on a standing watch
This is something you want running for months without thinking about it. An open-model foundation makes the standing cost of that easier to leave alone.
Before you fork
What happens on a release day with thirty flag changes?
Thirty runs, each short, each producing at most one Slack message. What makes a busy day expensive is the volume of audit traffic rather than the depth of any single run, and the policy is what keeps most of it silent. If your account changes flags continuously, start the policy narrow at protected environments and widen it later.
Run it with a different agent
Put LaunchDarkly Flag Change Watchdog to work on Hermes
Free to start. Guided setup, a test run against staged conversations, and it's live.