Hire an AI production yield and capacity reviewer

Everything it can hand back

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

• Mass reconciliation per batch: input, good output and scrap
• Net batch cost and cost per good kilogram, converted to your selling unit
• Contribution per unit and in total for each product
• Bottleneck hours needed against hours available, with unused hours or overload
• Missing facts, and checks that could not run

How it does the job well

• Reconcile to source documents, such as bank statements, ledgers and invoices, before reporting.
• Show the calculation, inputs and period for every figure.
• Label actuals, estimates and forecasts clearly.
• Send tax, legal and regulatory questions to a qualified professional.

Mistakes it avoids

• Mixing cash and accrual figures, or different periods, in one comparison.
• Rounding or formula errors that do not tie back to totals.
• Giving personal investment advice.

What a good result looks like

An example, not your task: You have batch results for two products and want to know which earns more per unit after scrap.

• YIELD BRIDGE. Input, good output and scrap per batch, net batch cost and cost per good unit.
• MIX CHECK. Contribution per unit and in total, hours needed against hours available, and any overload.
• SOURCES. Each input with its source, date, unit and period.
• MISSING and CHECKS MISSED. Each gap and the line it stops, and every check that failed or could not run.

How the work is checked

• Per-good-unit costs and mix quantities use the same physical unit. Planned volume is never raised from a contribution ranking.
• Each input traces to its source, date, unit and period, and unresolved MISSING: lines stay in the result.
• A real zero, missing evidence and an inapplicable figure are told apart. No plug forces a tie.
• End with CHECKS MISSED: none, or the exact checks still open.
• 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.

Capabilities

• Manufacturing yield cost bridge. Reconciles input mass to good output and scrap, values only evidenced scrap recovery, and divides net batch cost by good output. Converts cost to your selling unit. Hands step 2 cost per good unit and the conversion evidence. Check before moving on: mass and cash both reconcile.
• Product mix capacity checker. Builds each product's contribution from the step 1 cost and your selling prices, avoiding double counts of shared fixed costs. Multiplies planned units by bottleneck hours and compares with available hours. Reports unused capacity or overload. Keeps the mix as your proposal.

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 connect-production-yield-to-mix-contribution 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/connect-production-yield-to-mix-contribution/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

• For each product, one measured batch: input kilograms, good output and scrap (from production logs)
• The batch's input cost and conversion cash, such as labor and energy (from your accounts)
• What scrap sells for, with evidence (optional; without it no recovery is counted and the gap shows)
• The selling unit and price for each product (from your price list)
• Bottleneck hours per unit and the qualified hours available in the period (from machine records)
• The quantity you plan to make of each product

Helpful context (optional)

• Weighed batch records rather than recipe weights.
• Machine run logs that show actual bottleneck time per unit.
• A named reviewer who runs the line.

Tools and access

• A spreadsheet engine and file-capable AI: Builds a workbook with inputs, formulas and a checks tab you can click into. In plain chat it returns the same tables as text and says no workbook was made.
• Claude, ChatGPT or Gemini: Any of them can do these sums in a chat.
• An AI that can make spreadsheet files: It can build the workbook, recalculate it and check that it reopens.
• Node.js 20 or later (optional): Runs the small script that comes with the skill, for a second check of the numbers.

Functions and deliverables

• Production yield and capacity reviewer: Turn measured good output and scrap into unit costs. Compare product contributions and check the proposed workload against capacity.
  • Mass reconciliation per batch: input, good output and scrap
  • Net batch cost and cost per good kilogram, converted to your selling unit
  • Contribution per unit and in total for each product
  • Bottleneck hours needed against hours available, with unused hours or overload
  • Missing facts, and checks that could not run
• Manufacturing yield and unit cost calculator: Share batch weight, yield, costs and scrap prices. Get net batch cost and cost per good kilogram.
  • Good kilograms and scrap kilograms, which add up to the input
  • The money back from scrap
  • The net batch cost, input plus conversion less scrap
  • The cost per good kilogram
  • A check that good plus scrap equals input and that scrap money is counted once
  • A list of missing facts and checks it could not run
  • A small workbook with the same sums, if your AI can make files
• Product mix capacity checker: Share product quantities, margins and work hours. Check the mix's contribution and whether it fits the hours available.
  • Hours needed for each product and in total
  • Hours short or spare against the hours you have
  • Contribution for each product and in total
  • A clear note when the plan is over capacity, so it is not called feasible
  • A list of missing facts and checks it could not run
  • A small workbook with the same sums, if your AI can make files
• Production capacity checker: Share demand and output limits. Get plant use, efficiency, and gaps.
  • Utilisation by resource
  • The named bottleneck
  • Gap between demand and capacity
  • Options to close the gap, compared by cost and timing
  Source: Kishor Kukreja.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You have batch results for two products and want to know which earns more per unit after scrap.
• A product's real yield is lower than the recipe says and its cost looks wrong.
• You have planned quantities for next month and need to know if the bottleneck machine can run them.
• A buyer or lender asks how your unit costs and capacity numbers were worked out.

Limits to check before starting

• You want the best mix worked out for you. This tests a mix you choose and does not optimize.
• You have recipes or targets but no measured batch results. Measure real batches first.
• You have more than two products or several bottlenecks. Split the plan into pairs, or ask an analyst.
• You only need the cost per good kilogram. Use the Manufacturing yield and unit cost calculator on its own.

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.

• Download the workflow pack and give it to an AI that can read files, such as Claude, ChatGPT or Gemini. Use one that can make spreadsheets if you want a workbook.
• Attach your batch logs, cost records, price list and machine hours. Say the selling unit for each product and the period the hours cover.
• After step 1, check that input mass equals good output plus scrap for each batch, and that scrap value matches your sale evidence.
• After step 2, check that cost and quantities use the same unit, and that hours needed against hours available is clearly shown.
• Fill every MISSING line before anyone relies on the plan. Nothing is ordered or scheduled. A person who knows the line should review the bottleneck hours.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/connect-production-yield-to-mix-contribution 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.