CoreFit Athletics

No agent may send a direct communication to a member without human approval. All member-facing messages are drafted, queued, and approved.

Why: Members chose CoreFit for the personal touch. An obviously automated message destroys that illusion and devalues the brand.

Failure mode: In month 2, the lead nurture agent auto-sent a "We miss you!" email to 14 trial members who had visited the day before. Three replied asking if their check-in system was broken. Jamie spent an afternoon apologizing.

Scope: All agents, all member-facing output.

Every agent must pull fresh Mindbody data before acting on member status. Cached data older than 4 hours is considered stale.

Why: Members upgrade, freeze, cancel, and rebook constantly. Acting on stale data produces embarrassing errors.

Failure mode: The retention agent flagged member #4471 as at-risk (no visits in 12 days) and triggered a save offer -- $20 off next month. That member had upgraded to the $189/month premium plan 2 days prior. She received a discount offer on a plan she had just paid more for. She posted about it in the local Facebook group. 47 comments.

Scope: Retention agent, lead nurture agent, any agent reading member status.

The class scheduling agent owns schedule optimization recommendations but never modifies the Mindbody schedule directly. All changes go through location managers.

Why: Class schedules affect trainer pay, member routines, and room availability. A single bad swap cascades into staffing conflicts.

Failure mode: During a test phase, the scheduling agent auto-swapped a 6 AM yoga class to 6:30 AM based on attendance data. The 6 AM regulars -- 8 members who come before work -- showed up to a locked studio. Two cancelled memberships that week.

Scope: Class scheduling agent.

The trainer performance agent reports to Jamie only. No trainer sees their own performance data unless Jamie shares it in a 1-on-1 context.

Why: Raw performance metrics without coaching context feel like surveillance. Trainers need to trust the system, not fear it.

Failure mode: Early version CC'd a trainer on a weekly performance summary showing their class had the lowest average attendance. The trainer confronted Jamie in front of other staff. Took 3 weeks to rebuild trust.

Scope: Trainer performance agent.

Retention agent must cross-reference billing events (upgrades, plan changes, payment failures) from the last 7 days before classifying any member as at-risk.

Why: A member who just upgraded is the opposite of at-risk. A member whose payment failed may appear inactive but has a billing issue, not a retention issue.

Failure mode: See C002. The upgrade/at-risk collision was the single most embarrassing agent failure in CoreFit's history.

Scope: Retention agent, lead nurture agent.

Social media agent reads the class schedule and retention alerts before generating content. Posts must reflect current reality -- no promoting a class that was just cancelled, no "Join us this Saturday!" when the location is closed for maintenance.

Why: Social posts are public and permanent. A post promoting a cancelled class generates confused DMs and makes the brand look disorganized.

Failure mode: Social agent posted a "HIIT Marathon Saturday!" graphic for the downtown location. That location had cancelled Saturday HIIT two weeks prior due to low attendance. 11 people showed up to nothing.

Scope: Social media agent.

Lead nurture sequences pause automatically when a prospect books a trial class. Resume only if they no-show or don't convert within 7 days.

Why: Continuing to nurture someone who already booked feels tone-deaf and spammy.

Failure mode: A prospect booked a trial, received 3 more "Book your free class!" emails before attending. Replied "I already did, is anyone actually reading these?" Trial converted but trust was damaged from the start.

Scope: Lead nurture agent.

Trainer performance metrics use a 4-week rolling average, not single-week snapshots. Seasonal patterns (New Year surge, summer dip) are normalized against the same period last year.

Why: Single-week data is noisy. A trainer with one bad week due to illness shouldn't be flagged. Seasonal patterns create false positives.

Failure mode: January metrics showed every trainer "improving" dramatically. It was just the New Year resolution surge. Jamie almost gave bonuses based on phantom performance gains.

Scope: Trainer performance agent.

Location-specific context must be attached to every agent action. No agent operates in a "generic CoreFit" mode. Each location has different peak hours, demographics, and class preferences.

Why: The downtown location skews young professionals (25-35). The suburban location skews parents (35-50). Messaging that works for one alienates the other.

Failure mode: Lead nurture sent "Bring the kids to our Saturday Family Fitness!" to downtown prospects. Downtown has no kids' classes. 4 confused replies.

Scope: All agents.

When an agent triggers a member-facing action that results in a complaint, the entire outreach queue for that agent pauses until Jamie reviews and clears it.

Why: One bad message might be a fluke. Two bad messages in a row is a systemic problem. Pausing prevents compounding damage.

Failure mode: Before this rule existed, the retention agent sent 3 incorrect save offers in one week (stale data bug). By the third, Jamie's phone was ringing with upset members. Batch pause would have contained it to one.

Scope: All agents with member-facing output.

Mindbody API failures must be logged and surfaced immediately. Agents must not fall back to cached data for member-facing actions -- they must queue the action for retry.

Why: Mindbody has scheduled maintenance windows and occasional API outages. Agents acting on last-known-good data during outages caused the C002 incident.

Failure mode: During a 3-hour Mindbody outage, the scheduling agent used 6-hour-old data to recommend a class swap. The class had already been manually rescheduled by the location manager during the outage. Conflict created.

Scope: All agents using Mindbody data.

Jamie has final override on all agent recommendations. No agent escalates past Jamie to staff or members directly.

Why: Jamie is the brand. Members know Jamie. An agent that bypasses Jamie breaks the chain of trust that makes CoreFit work.

Failure mode: Not yet violated, but the boundary was tested when the retention agent flagged a high-value member and the draft "save" email sat in Jamie's queue for 3 days. The member cancelled before Jamie reviewed it. Now Jamie has a 24-hour SLA on retention flags.

Scope: All agents.

Trainers are not told which recommendations come from agents vs. Jamie's own analysis. The agent layer is invisible to staff.

Why: Trainers who know "a computer" is evaluating them behave differently -- they game metrics instead of improving. Jamie learned this from a gym owner friend who made the mistake of being transparent about it.

Failure mode: Hypothesized based on industry peer experience. One gym that revealed AI performance tracking saw trainers artificially inflating class check-ins by having members scan twice.

Scope: Trainer performance agent, scheduling agent.

The daily briefing must be compiled and delivered to Jamie by 5:45 AM local time. Jamie reviews before the 6:00 AM first class.

Why: Jamie's decision window is 15 minutes. A late briefing is a missed briefing.

Failure mode: Twice the briefing arrived at 6:10 AM due to slow Google Sheets API calls. Jamie had already started her day without it and missed a retention flag that could have saved a $149/month member.

Scope: All agents contributing to the daily briefing.

Member retention risk scoring uses a weighted model: visit frequency (40%), class variety (20%), social engagement (15%), billing consistency (15%), tenure (10%). No single factor triggers an at-risk flag alone.

Why: Single-factor triggers produce too many false positives. A long-tenured member who drops visit frequency for 2 weeks might be on vacation, not churning.

Failure mode: Early model used visit frequency alone. Flagged 23 members as at-risk in one week. 19 were on a local school spring break vacation. Jamie wasted 4 hours reviewing false flags.

Scope: Retention agent.

Lead nurture agent and social media agent share a content calendar. No nurture email contradicts or duplicates a social post within the same 48-hour window.

Why: Prospects who follow on social AND receive emails notice when messaging conflicts. It signals that nobody is paying attention.

Failure mode: Social posted "20% off first month!" while nurture sent "Free first week, no commitment!" to the same audience segment on the same day. Prospect screenshot both and asked which one was real.

Scope: Lead nurture agent, social media agent.

Any agent error that reaches a member triggers a post-mortem within 24 hours. The post-mortem must identify root cause, not just symptoms, and produce a rule update.

Why: Without post-mortems, the same class of error repeats with different specifics. The C002 incident could have been prevented if the earlier "We miss you" email error (C001) had produced a proper cross-reference rule.

Failure mode:

Scope: All agents.

Members who explicitly ask "Is this automated?" or "Am I talking to a bot?" must receive an honest answer routed through Jamie. No agent is authorized to deny being AI.

Why: Honesty is a brand value. Getting caught lying about automation is worse than admitting it.

Failure mode: Hypothesized. Not yet asked directly, but Jamie has a templated response ready: "We use AI tools to help us stay on top of things, but every message is reviewed by a real person before it's sent to you."

Scope: All member-facing output. ---