My AI Agent Isn't Allowed to Decide Anything

Description and use

Shot‑Delivery Guardian uses AI to analyze film production status and recommend which item can be delayed to avoid missed deadlines while respecting client approvals, director priorities, and dependencies.

Problem

When a film or TV show pipeline stalls, a human must quickly decide which work to delay to avoid missing deadlines, but this manual process is slow and error‑prone.

Outcome

In live tests, the system matched the fixed rule’s recommendation 60% of the time, identified backlog causes in 44 seconds on average, and never violated any of the safety constraints (client approvals, director flags, or downstream dependencies).

Workflow

• 1. Monitor pipeline stages for backlog and deadline status.
• 2. Query three monitoring tools: overall backlog, work item metadata, and detailed stage timing.
• 3. Apply the fixed rule to filter out client‑approved, director‑flagged, or dependent items.
• 4. Rank remaining items by slack hours and select the one with the most spare time.
• 5. Output the recommendation as a note on the operator’s dashboard.
• 6. Operator reviews and confirms the delay decision.

Evidence

I built a system that watches the work as it moves through each step, notices when a deadline is about to be missed, figures out why, and says which piece of work is safe to push back.

Source

The AI never got an important decision wrong, because I never let it make one.

Source

def score_bump_candidates(shots):
eligible = [
s for s in shots
if not s["client_approved"]
and not s["director_flagged"]
and not has_downstream_dependents(s, shots)
]
return sorted(eligible, key=lambda s: slack_hours(s), reverse=True)

Source

During one real test, the system hit a real problem reaching one of its three tools halfway through. It said so, plainly, in its own words.

Source

3 of 5 real tests matched what the fixed rule alone would've picked. About 44 seconds on average to look into a problem and respond, timed against the real live system. Zero broken rules across every single test.

Source