LAW.co Podcast

Eric Lamanna

Law.co, legal AI podcast for AI for law firms.

  1. 19h ago

    How AI Agents Interpret Statutes: Semantic Parsing for Legal Compliance

    When a legal AI agent delivers a compliance verdict, the real work happens long before the output appears. This episode of Law examines the semantic parsing infrastructure that transforms dense statutory text into structured, auditable reasoning — drawing on this deep-dive on AI statutory interpretation and legal compliance. Understanding how these systems are built is essential for any attorney or firm evaluating the trustworthiness of AI-driven compliance tools. The episode walks through the full picture of how statute-driven AI agents actually function, covering: Why statutes resist machine reading — hedged language, nested qualifications, scattered cross-references, and definition sections that quietly reshape entire bodies of text all make raw statutory prose structurally opaque to software.What semantic parsing actually does — a pipeline of tokenization, syntactic parsing, named entity recognition, coreference resolution, and temporal parsing converts free-form legal text into computable logic with traceable reasoning graphs.Semantic parsing vs. keyword search — keyword search locates a word; semantic parsing understands what that word does in context, distinguishing obligations from permissions and catching the inversions that "unless" quietly introduces.Handling definitions, cross-references, and recursive loops — disciplined parsers propagate binding definitions throughout downstream interpretation, navigate statutory cross-references, and impose depth limits to prevent runaway recursion from chained section references.Surfacing ambiguity rather than hiding it — well-designed systems assign calibrated confidence scores, present ranked alternate interpretations, and route genuinely open questions to human reviewers rather than manufacturing a false certainty.Version control as a compliance necessity — when thresholds shift or exceptions are added, systems must diff incoming text against stored versions, flag affected logic for revalidation, and preserve historical versions for matters governed by prior law.The episode also covers the guardrails that separate trustworthy systems from risky ones — audit logs, explicit jurisdiction selection, bias risk in training data and ontologies — and offers a practical framework for evaluating vendors: ask how the engine handles cross-references, demand to see the explanation layer, and test versioning and rollback before trusting any output. For more on building faster legal AI infrastructure, listen to the episode Compiler Tricks That Make Legal AI Pipelines Faster and Smarter. Law

  2. 1d ago

    Compiler Tricks That Make Legal AI Pipelines Faster and Smarter

    Software compilers and legal AI workflows seem worlds apart — until you examine the problems each is trying to solve. This episode of Law draws on this deep-dive on compiler-inspired optimization for legal agent pipelines to show how decades-old techniques from computer science map onto the inefficiencies that quietly slow down modern AI-assisted legal work. The result is a practical framework any firm can use to tune its pipelines — no advanced engineering background required. The episode walks through a series of compiler concepts and their direct legal AI equivalents, exploring both the efficiency gains and the governance guardrails that responsible deployment demands: Parsing contracts into structured trees — processing documents once into addressable objects (parties, obligations, definitions, remedies) so downstream agents follow pointers rather than re-reading entire files each time.Intermediate representations — converting incoming documents (PDFs, Word files, scanned images) into a single standardized layer upfront, so every agent works from consistent, format-agnostic input regardless of how the original arrived.Dead code elimination and deduplication — identifying redundant checks across multiple modules, caching results in a shared store, and consolidating duplicate risk flags so review dashboards surface clean, accurate warnings instead of inflated noise.Dependency-aware scheduling and parallel execution — mapping tasks as a dependency graph to run independent modules simultaneously, and using out-of-order execution to deliver fast-module results to attorneys before heavier modules finish — critical when filing deadlines are close.Batching and constant folding — grouping similar documents (like NDAs) into single jobs to reduce per-document latency, and encoding stable statutory references into versioned tables so agents never call an external API for information that rarely changes.Auditability as a non-negotiable constraint — every optimization step must store a timestamped diff between input and output, preserving rollback capability for attorneys and potential future court scrutiny.The episode also addresses the human side of optimization: translating server-rack metrics into billing-system language so partners and associates understand what changed, and building a team culture where pipeline improvements are celebrated rather than silently shipped. More from the show: if you're interested in how AI agents handle disagreement and reach decisions together, check out the episode When AI Agents Disagree: Consensus Algorithms in Legal Tech. Law

  3. 2d ago

    When AI Agents Disagree: Consensus Algorithms in Legal Tech

    Multi-agent AI systems are rapidly becoming a fixture in legal workflows — but when specialized tools disagree on the same contract clause, the problem isn't which tool is smartest. It's whether the system as a whole can resolve that conflict in a way that's principled, transparent, and defensible. This episode of Law explores this in-depth look at consensus algorithms for collaborative legal AI, examining how these frameworks turn competing AI outputs into auditable, reliable decisions fit for high-stakes legal practice. The episode walks through how consensus algorithms work in practice, why legal work demands a higher standard of rigor than most AI deployments, and what it takes to build a system attorneys can actually stand behind. Key points covered include: Why disagreement is the default, not the exception — layering multiple AI agents without a resolution protocol multiplies uncertainty rather than reducing it.Three core consensus models — majority voting (simple but flawed for specialized domains), weighted voting (where each agent's influence reflects its domain-specific track record), and Byzantine fault tolerance (engineered to stay reliable even when individual agents are corrupted or compromised).The infrastructure beneath the vote — agent registration, immutable ledgers, standardized query formats, and confidence-score calibration that prevents overconfident models from dominating the result.Built-in safeguards and tiebreakers — from second-round deliberations (where agents see each other's reasoning before voting again) to escalation paths that bring human reviewers in at the right moment.Continuous learning and security — dynamic weight adjustment as real-world outcomes are tracked, encrypted vote enclaves that protect proprietary model behavior, and anonymized audit logs built for regulatory scrutiny.The trust and culture challenge — why attorney adoption depends on demonstrating that the system defers to human override and is correctable, not infallible.The episode also looks at what's on the horizon: federated consensus networks that let firms pool anonymized performance benchmarks without sharing client data, and quantum-resistant cryptography to protect historical consensus logs against future computational threats. For more from the show on how AI systems navigate complex legal environments, check out the episode on Dynamic Ontology Mapping: How AI Agents Navigate Law Across Borders. Law co

  4. 3d ago

    Dynamic Ontology Mapping: How AI Agents Navigate Law Across Borders

    Cross-border legal work has always demanded more than fluency in multiple legal systems — it demands precision about when two concepts that share a name actually share a meaning. This episode of Law examines dynamic ontology mapping, drawing on this deep-dive article on AI agents navigating law across borders to explain how modern legal AI systems resolve jurisdictional vocabulary conflicts without burying attorneys in ambiguity or risk. The episode covers the full architecture of a dynamic ontology mapping system, from the foundational challenge of legal vocabulary to the governance safeguards that make it defensible in practice: The vocabulary tangle: Why seemingly identical legal terms — "lien," "charge," "pledge" — can diverge dramatically between civil-law and common-law jurisdictions, and why static legal dictionaries are dangerously inadequate for handling those shifts.Modular knowledge graphs: How jurisdiction-specific modules plug into a shared upper ontology built around universal concepts like Actor, Asset, and Remedy, keeping regional legal frameworks cleanly separated without sacrificing interoperability.Context-driven semantic alignment: How the system reads neighboring text, governing-law clauses, and forum metadata to rank candidate interpretations rather than committing to a single definition — keeping error rates manageable even under filing-deadline pressure.Ingestion, normalization, and version control: Why clean data pipelines, immutable document hashes, and commit-level governance over mapping rules are prerequisites for output that can withstand judicial or regulatory scrutiny.Conflict resolution and precedence logic: How the system distinguishes between concepts that validly coexist across jurisdictions and those that directly contradict each other, applying constitutional hierarchy and enactment-date metadata to pick the controlling rule — and documenting exactly why.Ethics, bias monitoring, and explainability: How disparity tracking across demographic attributes, rationale strings on every mapping decision, and expandable decision-tree visualizations combine to make AI-assisted legal analysis both auditable and professionally responsible.The episode closes by looking ahead to potential extensions of this technology into smart contracts and machine-readable legislation, and considers what it would mean for cross-border compliance workflows once technical standards begin to converge. For more from the show on how AI infrastructure handles sensitive information in legal environments, listen to Ephemeral Memory in Legal AI: Context-Aware Without the Privacy Risk. Law.ai

  5. 3d ago

    Multi-Modal Evidence Processing and AI Agent Chains in Legal Work

    Discovery in complex litigation has outgrown keyword search. When a single matter can pull in drone video, cloud storage logs, voicemails, scanned receipts, and decrypted messages — often within the same 48-hour window — the old model of siloed vendors and manual stitching simply cannot keep pace. This episode of Law explores the architecture that legal teams are starting to deploy to meet that challenge, drawing on this in-depth look at multi-modal evidence processing and AI agent chains in legal work. The episode walks through how specialized AI agents — each handling one discrete task — can be chained together into a unified pipeline that ingests every evidence format, processes it in parallel, and delivers structured, court-defensible output. Here's what's covered: Why traditional eDiscovery falls short: Text-search tools are ill-equipped for evidence buried in screenshots, audio files, or video frames — and the manual "stitching" between separate vendor tools is where time and accuracy are lost.What multi-modal processing actually means: Feeding video, audio, images, and documents into format-specialized models simultaneously, then connecting their outputs so they can be compared and reasoned over as a unified evidence set.How agent chains are structured: Each agent performs one focused job — transcription, facial recognition, named-entity extraction, tone classification — and passes structured tags downstream, making the whole pipeline modular and swappable.Chain of custody in an automated system: Every agent must log model versions, confidence scores, and processing timestamps to keep findings admissible and methodology explainable in court.Built-in safeguards: From encryption and role-based access at intake, to bias-monitoring agents that track demographic false-positive rates, to transparency reports generated automatically for judicial review.Operational and cost efficiency: Performance agents identify bottlenecks and parallelize processing; resource agents spin cloud GPUs up and down on demand — the difference between a pipeline that scales and one that collapses under trial pressure.The episode closes with a look at where this technology is heading — including foundation models that handle novel evidence types without retraining, and explainable AI that can highlight the specific frame or phrase that drove a classification decision. The core argument: this architecture isn't about replacing legal judgment, it's about clearing the formatting, reconciliation, and cross-referencing work that consumes attorney hours without requiring legal expertise. Firms that build and refine these pipelines on real cases before a high-stakes trial will carry a measurable edge into that courtroom. For more from the show, check out the episode on Ephemeral Memory in Legal AI: Context-Aware Without the Privacy Risk. Law

  6. 5d ago

    Ephemeral Memory in Legal AI: Context-Aware Without the Privacy Risk

    Privacy and performance don't have to be in conflict when deploying AI in a law firm — but achieving both requires deliberate architectural choices. This episode of Law examines ephemeral memory: a design pattern that gives legal AI agents the situational awareness they need to do meaningful work, while ensuring sensitive client information doesn't linger where it shouldn't. Drawing on this in-depth look at ephemeral memory in legal AI, the episode walks through the principles, the components, and the guardrails that make this approach viable for real-world legal teams. Here's what the episode covers: What ephemeral memory actually means: A short-lived context buffer that holds task-specific facts — client identifiers, session goals, relevant exhibits — for just long enough to be useful, then wipes them entirely rather than archiving them.Why legal work demands it: Attorney-client privilege isn't just a compliance checkbox; it shapes how context must be handled. A system designed to forget by default signals genuine respect for that relationship.Three core design elements: A rolling short-lived context buffer, on-demand retrieval with guarded recall (where each passage carries a retention policy that forces deletion after the current turn), and summaries that self-delete rather than silently compress privileged content into durable artifacts.What real guardrails look like: Policy-checked memory writes, storage-level erasure (not just a deletion flag), and audit logs that document the act of forgetting without reproducing what was forgotten.The performance case, not just the privacy case: Disciplined, small-scoped retrieval often outperforms large, noisy memory stores — reducing stale context and the kind of confident wrongness that erodes trust in AI outputs.Pitfalls to avoid: Backup policies that contradict retention rules, convenience-driven extensions to memory windows, and interfaces that give users no visibility into what the agent is currently holding.The episode closes with a reminder that ephemeral memory isn't a silver bullet — good prompts, solid retrieval logic, and thoughtful model choices still matter. But when forgetting is built into the architecture by design, privacy shifts from a liability to a genuine feature firms can speak to directly with clients and in security reviews. For more on how firms are building secure, scalable AI infrastructure, listen to the episode on How Law Firms Use Adaptive Load Balancing to Scale Legal AI Securely. Law

  7. 5d ago

    AI Is Rewriting the Economics of Tax Law — Here's the Data

    Tax law sits at the intersection of rule-based complexity and relentless process — which turns out to make it one of the most automation-exposed corners of the legal profession. This episode of Law unpacks a comprehensive market research report on AI in tax law, translating the data into a frank picture of where the practice is headed and what the economics will look like within five years. Here's what the episode covers: Market size and growth trajectory: AI-driven tax law workflows currently represent a $200–$400 million segment — with a credible path past $1 billion within five years, driven by structural conditions that make tax work unusually well-suited to automation.Why tax law is especially exposed: The practice is rule-based, document-heavy, and process-driven — the precise conditions under which AI systems consistently outperform human effort on speed and cost.Where disruption is hitting hardest: Research compression, drafting automation, proactive compliance monitoring, predictive risk modeling, and AI-assisted client intake are all reshaping the daily workflow of tax attorneys right now.The billable-hour math: The report estimates AI can automate 35–55% of total billable time in a typical tax practice — rising to 60–70% for highly structured tasks like document drafting and compliance analysis.The junior-associate pipeline problem: As entry-level research and drafting tasks are absorbed by AI, the traditional leverage model that funds law firm economics faces structural compression from the bottom up.The cost of waiting: Firms that delay adoption won't face sudden collapse — but will experience gradual margin erosion, pricing disadvantage, and commoditization of their core revenue base, often before the damage is visible on a financial statement.The episode also addresses the geographic concentration of competitive pressure, and names a competitive threat that goes beyond peer firms: the AI capabilities being embedded directly into tax, accounting, and enterprise platforms by companies like Thomson Reuters — systems that don't bill by the hour and don't require per-matter training. More from the show: if you're thinking about how firms manage the infrastructure behind legal AI at scale, the episode How Law Firms Use Adaptive Load Balancing to Scale Legal AI Securely is a natural companion listen. Law

  8. Jul 24

    How Law Firms Use Adaptive Load Balancing to Scale Legal AI Securely

    Running AI across a law firm isn't just a technology challenge — it's an operational and ethical one. This episode of Law explores how adaptive load balancing makes large-scale legal AI practical, drawing on this deep-dive on scaling legal AI securely. From deadline-driven filing windows to privilege reviews and intake processing, the episode unpacks the infrastructure decisions that determine whether AI workflows hold up under real pressure — or quietly fall apart. Here's what the episode covers: What adaptive load balancing actually does: Rather than routing AI requests in a fixed rotation, adaptive systems read live signals — queue depth, model health, available compute, and task complexity — to steer work toward the best available path in real time.Why legal workloads are uniquely uneven: A quick title search and a full privilege sweep are not interchangeable jobs. Mixing them in the same pipeline without coordination leads to queue starvation, tail latency spikes, and the kind of slowdowns attorneys remember.How policy becomes the traffic map: In law, routing rules aren't preferences — they're duties. Litigation work requires audit trails; sensitive matters require data locality; export-controlled items must stay in compliant regions. The router enforces these constraints, not just optimizes around them.The role of retrieval quality and human feedback: Smart routing catches weak retrieval before it produces bad output, and attorney behavior — which drafts get approved, which citations get rejected — becomes a continuous training signal that improves routing over time.Cost discipline and graceful degradation: Adaptive routing can schedule non-urgent jobs off-peak, prefer lower-token paths when quality is equivalent, and fall back to capable alternatives during outages — with transparent confidence flagging so users know when to apply extra scrutiny.Security as a system property, not an afterthought: Encryption, de-identification, access logging, and sensitivity-aware routing work together so that fast and secure become the same goal rather than competing ones.The episode closes with a broader argument: firms that modularize their routing logic, codify policies as versioned and auditable rules, and invest in observability aren't just getting faster workflows — they're building AI infrastructure that compounds in value over time, filing window by filing window. For more from the show, check out The Great Wealth Transfer: How AI Is Reshaping Estate Planning Law. Law

See All (58)

About

Law.co, legal AI podcast for AI for law firms.

Information

  • Creator
    Eric Lamanna
  • Years Active
    2026
  • Episodes
    58
  • Rating
    Clean
  • Copyright
    © 2026 Eric Lamanna
  • Show Website
    LAW.co Podcast