Research & writing

Evidence first.
Opinions second.

We write the way we build: sourced, reproducible, and fair to Agentforce. The series examines the platform job by job, asking what works, where completion breaks, and why. All of it is free on Substack.

Read on Substack

The founding problem

Can LLMs actually plan? The measured answer is no.

MOTA's founders have a long history of building enterprise platforms in highly regulated industries. With the arrival of LLMs in the enterprise, they grew uneasy as "hallucination" became an accepted explanation for wrong answers that carry real cost. The academic and industry research below says it formally: LLMs cannot plan or verify their own work, so both must live outside the model. It made that case on puzzles; MOTA brings it to live enterprise workflows.

SourceWhat it shows
Kambhampati et al., ICML 2024: LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks · PDF · slides · talkLLMs cannot plan or self-verify on their own. The prescription is an external planner and sound verifiers around the model.
Valmeekam et al., NeurIPS 2022: PlanBenchThe standard benchmark for LLM planning. Progress across model generations has been, in the authors' words, surprisingly slow.
Valmeekam et al., NeurIPS 2023: On the Planning Abilities of LLMsGPT-4 solved roughly a third of simple block-stacking problems, and close to none once the object names were disguised. The plans looked plausible and were wrong.
Stechly et al., 2024: On the Self-Verification Limitations of LLMsAsking a model to check its own work does not rescue performance. Verification has to come from outside the model.
Valmeekam et al., 2024: LLMs Still Can't Plan; Can LRMs?Reasoning models improve on PlanBench but degrade as plans grow longer, at far higher cost. The gap narrows; it does not close.
Apple ML Research, 2025: The Illusion of ThinkingOn controlled puzzles, reasoning models collapse to zero accuracy past a complexity threshold, even when handed the algorithm.
AIGuys (Medium): LLMs Still Can't Plan and ReasonA widely read practitioner walkthrough of the evidence, for readers who want the argument without the notation.
FireCompass: Why LLMs Cannot PlanA practitioner's summary of the same evidence, from a team building agents in production.
Salesforce AI Research, 2025: CRMArena-ProThe enterprise confirmation: agent accuracy falls from 58% to 35% when CRM flows go multi-turn.

Our reading of the field, offered in good faith to encourage debate. The researchers cited here are independent of MOTA and do not endorse it. If new evidence shows models planning reliably, the Completion Index will report it.

The Agentforce series

Job by job, with sources.

We also publish on LinkedIn and Medium, where new analysis appears as it ships.

In the trade press

The workflow problem, on the record.

Across 2025 and 2026, enterprise IT coverage converged on one finding: AI workflows break in production without deterministic control, and the burden of adding it has landed on customers.

CoverageWhat it reports
Salesforce Engineering, Oct 2025: Toward guided determinismSalesforce's SVP of AI Research: its "most sophisticated customers are struggling" to keep autonomous agents on-topic in critical workflows. The prescribed fix is deterministic structure over agent execution.
CIO.com, Jan 2026: Agentforce recalibration raises costs and complexity for CIOsAnalysts at Greyhound Research and Avasant on the shift to Agent Script: autonomy without guardrails is unscalable, ROI timelines stretch, and the work of workflow mapping, testing and governance now falls on customer teams. In regulated industries, deterministic automation "is not optional; it is essential."
VentureBeat, 2026: The workflows breaking enterprise AISalesforce's own framing at the Agentforce Operations launch: many enterprise workflows were designed around human judgment and break when agents follow them literally.
CIO.com, 2026: Why agentic architecture is still so puzzlingIT leaders rolling out dozens of agents still lack the architecture underneath them; most agents stall at pilot on workflow redesign, measurement and security.

Our reading: the market has agreed that determinism is required. The open question is whether every customer should build it themselves, one script at a time. MOTA's answer is a completion layer that does the planning, gating and audit as a product.

Primary sources

What we build on.

SourceWhat it establishes
CRMArena-Pro, Salesforce AI Research (arXiv:2505.18878)Agent accuracy falls from ~58% single-turn to ~35% multi-turn on realistic CRM flows; near-zero default confidentiality awareness
Gartner press release, June 2025Over 40% of agentic AI projects predicted canceled by end-2027; costs, unclear value, inadequate risk controls; "agent washing"
Forrester, Predictions 2026: Automation at the Crossroads<15% of firms to enable agentic features; deterministic automation as the backbone of reliability and compliance; process intelligence to rescue 30% of failed AI projects
IDC, Agentic AI Is Breaking Your ROI ModelNew agent metrics: autonomous resolution rate, decision quality, escalation accuracy
IBM, Straight-Through ProcessingThe enterprise standard for flow completion: end-to-end, zero-touch

See how these frame the Completion Index →