# AI for Operations, Supply Chain & Project Management URL: https://justuju.org/role/operations/ For your role Operations is process, and process is what agents are built for: take a request, check the rules, act across systems, report. AI moves from summarising work to doing steps of it, so the design question becomes which steps, and who handles exceptions. ## How AI is changing this work - Status and coordination work, such as updates, chasing and routing, is done by AI inside the work tool. - Process automation grows from fixed scripts to agents that handle varied inputs and decide the next step. - Forecasting gains ready-made models that predict demand without months of custom modelling. ## Key layers, most important first ### 1. Layer 8 · Agents URL: https://justuju.org/layer/agents/ Why it matters: An operations process is a loop of check, decide, act and hand over. Agents now run those loops across systems, alongside existing automation and people. What to do here: - Agent plus fixed automation: Use fixed rules where steps never vary and an agent where inputs are messy; let one process hold both. (see https://justuju.org/concept/agent-loop/) - Humans on exceptions: Route anything unusual, costly or irreversible to a named person, with the context attached. (see https://justuju.org/concept/agent-permissions/) - Many agents, one conductor: Coordinate specialist agents through one layer that tracks state and can pause or retry. (see https://justuju.org/concept/multi-agent/) - Screens as a last resort: Where an old system has no interface for software, an agent can use its screens like a person. (see https://justuju.org/concept/computer-use/) Examples as of 2026-11-11: ServiceNow AI Agents (https://www.servicenow.com/products/ai-agents.html); UiPath Maestro (https://www.uipath.com/platform/agentic-automation/business-orchestration) ### 2. Layer 9 · Applications & Interfaces URL: https://justuju.org/layer/applications-interfaces/ Why it matters: Project and work tools are where plans, tasks and updates live. AI inside them removes the reporting work that surrounds real work. What to do here: - Automatic status: Generate the weekly update from task activity, and flag projects drifting off plan. (see https://justuju.org/concept/embedded-ai/) - Intake and routing: Sort incoming requests, fill missing details and assign them by rule. (see https://justuju.org/concept/copilots/) - Ask across tools: Search tasks, documents and chat in one question, limited to what you may see. (see https://justuju.org/concept/chat-assistants/) Examples as of 2026-11-11: Asana AI Teammates (https://asana.com/product/ai/ai-teammates); Atlassian Rovo (https://www.atlassian.com/software/rovo) ### 3. Layer 7 · Orchestration & Tooling URL: https://justuju.org/layer/orchestration-tooling/ Why it matters: Agents are only useful if they can reach your systems. This layer connects them to orders, stock, tickets and calendars, with permissions and tests. What to do here: - Systems as tools: Expose each system's actions, such as create order or update ticket, as named tools with limits. (see https://justuju.org/concept/tool-use/) - Procedures as context: Give the agent your written operating procedure; unclear procedures produce unclear agents. (see https://justuju.org/concept/context-engineering/) - Dry runs: Replay last month's real cases through a new agent and compare with what staff did. (see https://justuju.org/concept/guardrails-evals/) Examples as of 2026-11-11: Zapier MCP (https://zapier.com/mcp); n8n (https://n8n.io/); Microsoft Copilot Studio (https://www.microsoft.com/en-us/microsoft-365-copilot/microsoft-copilot-studio) ### 4. Layer 5 · Foundation Models URL: https://justuju.org/layer/foundation-models/ Why it matters: Not every model is a chat model. Models trained on time series forecast demand and load out of the box, and belong in the planner's toolkit. What to do here: - Forecast without custom training: Try a ready-made forecasting model on your history before commissioning a bespoke one. (see https://justuju.org/concept/specialised-models/) - Use the right model for the task: Language models explain and plan; numeric forecasts come from numeric models and solvers. (see https://justuju.org/concept/specialised-models/) - Reasoning for planning: Use a model that thinks in steps to draft plans and spot conflicts, then verify with real constraints. (see https://justuju.org/concept/reasoning-models/) Examples as of 2026-11-11: Chronos (Amazon) (https://github.com/amazon-science/chronos-forecasting); TimesFM (Google Research) (https://github.com/google-research/timesfm) ## High-leverage use cases - Request intake and routing: Classify, complete and assign incoming requests across teams. - Status reporting: Project and portfolio updates written from task data, with risks flagged early. - Exception handling: Agents resolve routine order, delivery and invoice exceptions and escalate the rest. - Demand and capacity forecasts: Baseline forecasts from a ready-made model, reviewed by a planner. - Procedure upkeep: Draft and update operating procedures from how work is actually done. ## Start here: the next 30 to 60 days - Week 1 to 2: Pick one high-volume process and write its steps, rules and exceptions on one page. - Week 3 to 4: Turn on automatic status updates for one project and compare with the manual report. - Day 30 to 60: Pilot an agent on that process in dry-run mode: it proposes, a person acts. Measure agreement. - Day 30 to 60: Run a ready-made forecasting model on two years of history and compare with your current forecast. ## Risks and pitfalls - Automating a broken process: An agent runs a bad process faster. Fix and write down the process first. - Errors that compound: A small mistake early in a long chain grows with each step. Add checkpoints and keep chains short. - Irreversible actions: Orders, payments and deletions need a confirmation step or a limit. Source: https://genai.owasp.org/2025/12/09/owasp-top-10-for-agentic-applications-the-benchmark-for-agentic-security-in-the-age-of-autonomous-ai/ - Nobody owns the agent: Each agent needs a named owner, a log and a way to switch it off. - Language models doing arithmetic: Quantities, dates and totals should come from systems and solvers, not from a model's recall. ## Sources - ServiceNow AI Agents (servicenow.com): https://www.servicenow.com/products/ai-agents.html - UiPath Maestro (uipath.com): https://www.uipath.com/platform/agentic-automation/business-orchestration - Asana AI Teammates (asana.com): https://asana.com/product/ai/ai-teammates - Atlassian Rovo (atlassian.com): https://www.atlassian.com/software/rovo - Zapier MCP (zapier.com): https://zapier.com/mcp - n8n (n8n.io): https://n8n.io/ - Microsoft Copilot Studio (microsoft.com): https://www.microsoft.com/en-us/microsoft-365-copilot/microsoft-copilot-studio - Chronos (Amazon) (github.com): https://github.com/amazon-science/chronos-forecasting - TimesFM (Google Research) (github.com): https://github.com/google-research/timesfm - OWASP Top 10 for Agentic Applications: https://genai.owasp.org/2025/12/09/owasp-top-10-for-agentic-applications-the-benchmark-for-agentic-security-in-the-age-of-autonomous-ai/ - NIST AI Risk Management Framework (AI RMF 1.0): https://www.nist.gov/itl/ai-risk-management-framework --- Justuju · https://justuju.org/ · Content CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote with a link to the page.