"AI-powered" now appears on a great many consulting websites, and it can mean almost anything: a chatbot beside a dashboard, AI-written copy, or real analytical tooling. The phrase alone tells a buyer nothing about what the AI does or who checks it.
Here's what it looks like when AI is actually wired into the forensic schedule analysis workflow, not as a gimmick, not as a chatbot wrapper, but as production tooling built by a scheduler with twenty-four years in industry who writes delay claims and carries them through negotiation, mediation and arbitration preparation. And here's where the human still has to show up.
What CPP Actually Built
Critical Path Partners runs its forensic work on an AI-native analysis stack. The entire forensic workflow, from XER parsing to DCMA assessment to windows analysis to collapsed as-built validation to Monte Carlo risk quantification to claims packaging, runs on purpose-built tools. Thirteen of them, from the parser through the Monte Carlo and the claim workbench, are on a public server anyone can connect to. The rest, claims packaging among them, run inside engagement work.
This isn't a SaaS product built by a software company that hired a scheduler as a consultant. This is the other way around: I'm a working forensic analyst who built my own tools because the existing ones didn't do what I needed, then made the core of it available for AI assistants to call directly.
The numbers are specific because the tools are real:
Every one of those twenty-one skills is executable code, not a generic prompt template and not a chatbot persona. The forensic ones carry their AACE recommended practice references, heuristic gates and attribution math with them. You can browse every skill and what it does at built-on-claude.html.
This post counted sixteen skills when it was published on 3 May 2026. Five more were added in July 2026: impacted as-planned, concurrency and apportionment, constructive acceleration, claim provability and measured mile. The count on this page now reads twenty-one, and each skill is listed on the page linked above. One line was corrected in the same pass: nine skills sit behind the thirteen MCP tools, not ten. On 1 October 2026 two more were corrected. The closing section now says which tools are public: the thirteen MCP tools, with the other twelve skills running inside engagement work. And the line count is the one measured on 30 September 2026: over 100,000 lines of Python in the scripts of the twenty-one skills.
Three Layers of the Stack
The system is built on three pieces of Anthropic's AI infrastructure, all in production. If you don't care about the technical architecture, skip to the next section. But if you're a construction lawyer evaluating expert tools or a PM trying to understand what you're looking at, this matters.
Layer 1: Claude Skills
Each Skill is a self-contained capability: code, methodology references, and trigger documentation that the AI loads only when the task requires it. There's a Skill for XER parsing. A Skill for DCMA 14-point assessment. A Skill for windows analysis. A Skill for collapsed as-built. A Skill for Monte Carlo risk simulation. A Skill for claims packaging. Twenty-one in total, each one built to produce a specific deliverable.
The key distinction: these aren't prompt templates that ask an AI to "act like a forensic analyst." They're executable code, and the analysis Skills perform the actual calculations on real schedule data. When the windows analysis Skill runs, it's computing critical path shifts across every analysis period, applying conservation-rule delay attribution, and generating per-window activity-level results. The AI orchestrates the workflow. The Skill does the math.
Layer 2: MCP Server (Model Context Protocol)
Nine of those skills are published as thirteen tools on a public MCP server at mcp.criticalpathpartners.ca. MCP is an open standard from Anthropic that lets any compatible AI assistant call external tools. That means Claude (in the browser, on desktop, or via API), Cursor, Cline, and any other MCP-aware client can connect to CPP's engine and run forensic analyses directly.
No signup. No license key. No sales call. Connect the server, drop your XER, and run a DCMA 14-point assessment or a forensic windows analysis in your own AI session. The tools are just there, the same way a construction lawyer can call an expert and say "I need a delay analysis by Friday."
Layer 3: Agent Orchestration (Claude Code)
The third layer is where the AI decides which tools to call, in what order, and what to do with the results. A full forensic delay claim doesn't run on one tool. It chains four or five: parse the XER, run the windows analysis, validate with collapsed as-built, quantify risk with Monte Carlo, then package the findings into a claims submission with cover letter, per-event exhibits, and supporting documentation.
In engagement work that sequencing is done by Claude Code agents under the analyst. The session keeps a record of each tool call with its inputs and outputs, so a conclusion can be traced back through the chain to the XER data that produced it. The analyst reviews each step and signs the result.
The fastest way to understand what this does is to use it. Connect the MCP server from your own Claude session in 30 seconds: here's the JSON snippet. Or drop an XER into the live engine without connecting anything.
What the AI Actually Does
Parses a 97,000-line, 5.4 MB XER in 0.35 seconds (measured, median of three runs on a 2023-era Windows laptop; 18 tables, 2,877 activities, 7,744 relationships) and surfaces the structural problems (missing logic, orphan activities, constraint-driven false criticality, calendar mismatches) that a human analyst would spend half a day identifying manually.
Runs a DCMA 14-point assessment in seconds that would take a human analyst four to six hours to produce, including the interactive dashboard, drill-down on every criterion, and specific fix recommendations per activity.
Sequences a full forensic analysis chain (windows analysis into collapsed as-built validation into Monte Carlo risk quantification into claims packaging) in a single orchestrated workflow, with every intermediate result available for review.
Generates the dashboards, CSVs, narratives, and exhibits that make up the deliverable set. Interactive HTML forensic dashboards. Per-window delay attribution tables. Executive summary reports. Claims-ready cover letters and per-event exhibits.
Handles the mechanical precision that humans are bad at. Conservation-rule arithmetic across twenty analysis windows with concurrent delays in fourteen of them. Activity-level slip tracking across 3,000+ activities. Baseline-vs-current variance calculations on every predecessor relationship in the network. The AI doesn't get tired, doesn't transpose numbers, and doesn't skip Window 12 because it's Friday afternoon.
What the AI Does NOT Do
This is the part that matters more than everything above, and it's the part that every "AI-powered" marketing page conveniently leaves out.
It doesn't write expert opinions. An expert opinion is a professional judgment backed by experience, credentials, and the willingness to defend it under oath. The AI produces the analysis. The analyst writes the opinion, signs it, and gives the evidence if the matter goes to a hearing. Those are different things and they cannot be substituted.
It doesn't make judgment calls on concurrent delay attribution. The conservation-rule math has gates: decision points where the analyst has to determine whether two concurrent delays are truly independent, whether one is pacing the other, or whether the contractor's delay was caused by an upstream owner delay. Those calls require reading the correspondence, understanding the site conditions, and knowing what "reasonable" looks like in that specific construction context. The AI flags the decision point. The analyst makes the call.
It doesn't survive cross-examination. Nobody is putting an AI on the stand. When opposing counsel challenges a specific delay attribution in Window 7, they're challenging the analyst's interpretation of the evidence, not the software that ran the calculation. The tools produce defensible analysis. The analyst defends it.
It doesn't replace the pattern recognition that takes decades to develop. Knowing that a particular constraint configuration is hiding a float manipulation. Recognizing that an owner's planner is refusing to provide native schedule files because the as-built data would undermine their position. Seeing that three apparently unrelated RFI delays all trace back to the same incomplete design package. That pattern recognition comes from having done the work on dozens of projects across twenty-four years, not from a training dataset.
Building AI tools is a software problem. Writing the methodology in a way that a tool can execute correctly, defensibly, and without fabricating conclusions requires having actually written delay claims and carried them through negotiation, mediation and arbitration preparation. The forensic skills carry the disclosures, the heuristic gates, the conservation-rule attribution math, and the audit-trail discipline that comes from twenty-four years of doing the work. That's the part that doesn't get replicated by downloading a framework and prompting an LLM.
How CPP Works
CPP pairs public, testable tooling with a working forensic analyst. The engine is free to try; analyst engagements are priced per matter. The tooling is public, testable, and open for anyone to connect to and evaluate before they ever pick up the phone.
That's a deliberate decision. The engine is free because the engine is the easy part. The hard part is the interpretation, the expert opinion, the claims strategy, the cross-examination preparation. That's what you book a consultation for. Letting people run the engine first means they show up to that conversation already understanding what the tools can do and what they need the analyst for.
Why This Matters Right Now
AI assistants are becoming the default research interface for construction lawyers, project managers, and claims consultants. When a construction lawyer asks their AI assistant to "run a DCMA 14-point health check on this XER and tell me which contractor's schedule looks defensible," the tools that are wired in get called. The tools that exist as PDFs on a consulting firm's website do not.
CPP's thirteen MCP tools are callable from any MCP-aware AI client right now: Claude in the browser, Claude Desktop, Cursor, Cline, and any future client that supports the protocol. That means the engine is discoverable and usable by every AI assistant that a construction professional might be working with, without CPP needing to be in the room.
This is not a future-state roadmap. Every tool described in this post is in production. The thirteen MCP tools are publicly accessible today, and anyone can test them: they include the XER parser, the DCMA assessment, the forensic windows analysis, the collapsed as-built, the Monte Carlo simulation, and the claims workbench. Nine of the twenty-one skills sit behind those thirteen tools. The other twelve run inside engagement work. Behind them are over 100,000 lines of Python in the skills and the 1,500 passing tests of the CPM engine.
Twenty-four years of forensic methodology, twenty of them in nuclear and energy programs, encoded into production tools that run on the same AI stack that's becoming the infrastructure layer for professional services. I built these tools because I needed them for my own analysis work. I made them public because the industry needs them too, and because the best way to demonstrate what you can do is to let people try it themselves.
See the engine. Talk to the analyst.
Drop your XER into the live engine and see what comes back. Or connect the MCP server to your own Claude session. When you're ready for the part the AI can't do, book a consultation.
Try It Live → Talk to CPP →