Hire an AI project delay test reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A delay trend brief: waiting time and working time by stage, against the baseline
• A list of new delay patterns, or a clear note that there is no new pattern this week
• A keep, revise or stop call on the fix, with the sample size behind it
• A note on shared dependencies when they moved
• MISSING lines for stages with no timing, and a record for the next week

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Repeating last week's findings as new.
• Reading a single late task as a pattern.
• Calling a script result checked when the scripts were not run. A result read by hand is weaker than one run by script, so say so at the top of the brief.
• Acting on a "stop" call. The user, or the owner of the fix, decides.
• Describing installation as a running automation.
• Treating opinions or one loud request as proven demand.

What a good result looks like

An example, not your task: You tried a change, such as a faster review step, and want to know after a few weeks if it helped.

• Trend by stage. Waiting time and working time for each stage, against the baseline, with the number of tasks behind each figure.
• New patterns. Any stage that moved past your limit, with the task IDs that show it. If none moved, it says so.
• Dependencies note. Shared dependencies that moved and the projects they touch, from the Project risk and portfolio manager.
• Recommendation. Keep, revise or stop for the fix you are testing, with the sample size and how much more evidence is needed.
• Improvement plan. When a new pattern needs a change, one small test with an owner, a measured baseline, a review date and a success check.
• MISSING lines and CHECKS MISSED. Stages with no timing, and every check that could not run, such as scripts that were read but not run.

How the work is checked

• Waiting time and working time are shown apart, with the same units as the baseline.
• Every figure shows the number of tasks behind it.
• No sentence says the fix caused a change.
• A thin sample led to keep and a note on how much more evidence is needed.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Ed Catmull would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read last week's baseline. Loads the task group, how the baseline is defined, the sample size, the fix being tested, the review date and links to the evidence. A first run builds the baseline with you.
• Add new finished tasks. Counts only tasks finished since the last review. A task missing a start or finish date is listed, not counted.
• Compare with the baseline. For each stage, compares waiting time and working time with the baseline. A new pattern is a move past your limit. With no limit given, it proposes a plain one and labels it ASSUMPTION for you to change.
• Run the right workflow. A new pattern runs the Trace why work keeps missing deadlines workflow, with the Process bottleneck finder, the Outside view timeline estimator and the Change rollout planner. Moved dependencies run the Project risk and portfolio manager.
• Judge the fix. Gives a keep, revise or stop call with the sample size shown. If the sample is too small, the fix stays unchanged and the brief says how much more evidence it needs.
• Check and save. Checks that only comparable tasks were compared and that no cause is claimed. Saves the files, a run log and the new record, and keeps the old record.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id weekly-project-delay-evidence-assistant only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/weekly-project-delay-evidence-assistant/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Dated task updates with task ID, stage, start date, wait time or wait dates, and finish date (from your project tool export, a spreadsheet or status notes)
• The original estimate for each task
• The actual finish date for each completed task
• The fix you are testing: what changed, the date it started and the review date
• How far a stage's waiting time may move before it counts as a new pattern (optional; the agent proposes a rule if you give none)
• Last review's record (optional, from the second week on)

Helpful context (optional)

• An export from your project tool with start, wait and finish dates.
• Notes on what the fix changed and when.
• A list of shared dependencies across projects.

Tools and access

• A capable chat AI with file support: Keeps the record between weeks. An AI that can run Python can also run the scripts that come with the Project risk and portfolio manager.
• An AI that can run code: Meaningful delay numbers need arithmetic on many rows. A code-capable AI checks the sums. A plain chat AI does them by hand and flags that.

Functions and deliverables

• Project delay test reviewer: Compare new task times with the original baseline. Get delay patterns and a keep, revise or wait recommendation for the current test.
  • A delay trend brief: waiting time and working time by stage, against the baseline
  • A list of new delay patterns, or a clear note that there is no new pattern this week
  • A keep, revise or stop call on the fix, with the sample size behind it
  • A note on shared dependencies when they moved
  • MISSING lines for stages with no timing, and a record for the next week
• Recurring work delay reviewer: Share repeated work steps, owners and timing records. Get likely delay points, a grounded timeline estimate and a small change to test.
  • A delay map: each stage with its owner, working time, waiting time and rework
  • A ranked list of bottlenecks, each with the records behind it
  • Likely causes, marked as proven by records or as a guess to test
  • How far your estimates run off, with the range and the number of jobs used
  • A plan for one small change, with a starting number, an owner and a review date
• Project risk portfolio planner: Share project risks, scores, owners and resource needs. It compares exposure and workload, then drafts priorities and status for review.
  • Risk register with expected cost
  • Priority ranking of projects
  • Resource load check
  • Health scores and status colours
  • Executive summary
  Source: Alireza Rezvani.
• Early project progress reviewer: Review an unfinished project against its earlier versions. Get a proposed keep, change or stop decision, the evidence behind it and a review date.
  • A dated timeline, judged against the project's own earlier versions
  • A result for the notes test: what changed after each round
  • A read on whether the team still believes, or the one private question to ask each person
  • One of four calls: keep protecting, change the approach, change the lead or stop
  • The evidence, a date to look again and what would flip the call
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
  • Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
  • The answer or the work, in Ed Catmull's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You tried a change, such as a faster review step, and want to know after a few weeks if it helped.
• Tasks keep finishing later than estimated and you cannot say which stage holds them up.
• A key dependency moved and several projects may slip together.
• You review work every week and want the trend, not a fresh guess.

Limits to check before starting

• One project with no finished tasks yet. There is no baseline to compare. Use the Recurring work delay reviewer workflow for a first pass.
• Tasks with no dates. Add start and finish dates first. Without them the agent can only ask for them.
• Only shared dependencies or risks across projects changed. Use the Project risk portfolio planner on its own.
• You want a new finish date for one project. Use the Past-project timeline estimator.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Add the agent to Claude, ChatGPT or Gemini with its helpers, the Trace why work keeps missing deadlines workflow and the Project risk and portfolio manager. Or download the pack and attach it.
• Paste this week's task export (one row per task: ID, stage, start date, wait, finish date, estimate; dates as YYYY-MM-DD, with the timezone) and describe the fix you are testing. Say what a new pattern means to you, or let the agent propose a rule. From week two, paste last week's record.
• Remove staff names and other personal details from the export before you paste it. Task IDs and stage names are enough.
• Read the trend brief. Check the sample size before you believe any change. The first run only builds your baseline, so it gives no keep, revise or stop call yet.
• If the brief says the evidence is too thin, leave the fix as it is.
• Change your plan yourself if you agree. The agent changes nothing. After a "stop" call, you or the person who owns the fix decide what happens next.
• The Project risk and portfolio manager comes with Python scripts. In a chat-only tool the AI reads the numbers instead of running them, and says so under CHECKS MISSED.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-project-delay-evidence-assistant for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.