We need experience to get a job. We need a job to get experience. Let's break that loop.
So "years of experience" doesn't start at zero.
We build production AI systems for communities that need them most.
If you want hands-on engineering tied to partner needs, there is room to contribute here.
From student to engineer. For real.
Faculty & Advisors
“Research rigor means being able to show your work at every step — the methods, the assumptions, the limitations...”
“Most agentic AI research focuses on what these systems can do. We at AnacodicAI Labs focus on who they're for...”
Why we exist
Some communities have a clear need for technology and no path to it. Not because the problem is unsolvable, but because no one is paid to solve it for them.
We build in that gap: students gain real-world experience on real data, held to a peer-reviewed evidence bar.
The rigorous, publishable method & capability work behind the mission — and where students earn Q1 authorship with faculty. Frugal, interpretable, grounded.
Research behind it
MAD / quantile family · stable-dist. naive Bayes · ensembles · Pareto/Gini approx
2 research · 0 projects
Source · Elementary & Robust Distribution Shape Analysis (JETA · MDPI) · Code · c-trapezoid-quantile-metrics
Clinicians without current evidence; expertise stuck in rich hospitals.
Research behind it
burn / craniofacial / hand RAG · sickle-cell maculopathy · treatment planning
2 research · 1 project
Source · PMC · AI & telemedicine in rural communities (2025) · PMC · Agentic AI & specialist health services (2025) · +1
AI's energy and water cost; clean-energy access; grid reliability where the margin for error is thin.
Research behind it
low-carbon OECD/BRICS · hourly electric load · marine pollution · ocean drifters
4 research · 0 projects
Source · Carbon Cost of Intelligence (Energies · MDPI) · FAS · Measuring AI's Energy Footprint (2024) · +1
Teacher shortage; feedback that can't scale to crowded classrooms.
Works
Research behind it
teaching Python · data-sci via Kepler · adaptive learning
2 research · 1 project
Source · UNESCO · Global Report on Teachers (2024) · OECD · Education at a Glance 2024 · +1
Local businesses priced out of the tech big chains take for granted.
Works
Research behind it
cost-constrained BI · LLMs & entrepreneurship · startup survival
1 research · 2 projects
Source · World Bank · MSME finance & digital access · IFC · Digital divide in business intelligence · +1
The written & cultural record locked away — unreadable scripts, untranslated books, looted art.
Research behind it
Euler catalog · Roman-coin Benford · Greek-vase geometry · numismatics
2 research · 0 projects
Source · Washington Conference Principles on Nazi-Confiscated Art · Getty · Provenance Index · +1
Medicines & goods that never reach the regions that need them.
Research behind it
"safer medicines" pharma logistics · supply-chain AI integration
1 research · 0 projects
Source · Operational Resilience Under Carbon Constraints (Systems · MDPI) · Carbon Cost of Intelligence (Energies · MDPI)
Skill-rich craft communities locked out of premium markets.
Research behind it
craft / market-access · informal-economy earnings gaps
1 research · 0 projects
Source · Reimagining craft for community development (T&F) · IIT Kanpur · YUKTI craft kārkhānās · +1
How we bridge it
You bring the skills; they hold the mandate. We run the collaboration like research and ship like production. Clear scope, honest review, systems held to a production bar, not a demo bar.
Students gain production commits, published research, and documented contributions. See:
Where we build
Rooted at Boston University.
Built for where infrastructure, capital, and specialist access run out first.
Open research threads · What we're researching right now
Safety-Critical Recommendation AI
Recommendation systems optimize for what a user will prefer — but when a wrong suggestion can cause real harm, such as recommending a dish containing an allergen to someone who must avoid it, preference and safety become competing objectives inside one model. This research examines how safety should be enforced in recommendation systems when the cost of an error is high.
Rolling basis
AI Energy Research
Extension of the published CCI energy benchmarking framework to deployment environments with infrastructure constraints. Energy cost characterization and carbon-aware model selection studied under constrained deployment conditions.
Rolling basis
Energy Forecasting AI
Grid operators schedule generation and hold reserves against a forecast of tomorrow's electricity demand, but a single point forecast hides what a dispatch decision actually needs: how wrong it could be, and when. This research asks how a forecasting system can report honest, trustworthy uncertainty that still holds up when demand shifts into an unusual regime, framed as decision support for the control room rather than autonomous dispatch.
Rolling basis
Translation & Heritage AI
Millions of digitized books and manuscripts are readable as images but inaccessible as meaning — locked behind old scripts, dead and low-resource languages, and OCR that quietly corrupts the text before anyone translates it. LLMs can now translate book-length text well enough to be useful but not reliably enough to trust blindly, and the most accurate models are the most expensive — so cost and accuracy pull against each other. This research asks how to turn scanned books and historical manuscripts into accurate, citation-traceable translations at a cost that makes translating whole libraries — not just single pages — actually feasible.
Rolling basis
What we're building right now
Recommendation AI
Recommending food is easy — until a wrong suggestion triggers an allergic reaction. A conversational recommendation system that treats safety as a separate, non-negotiable check: a reasoning-and-acting (ReAct) orchestrator drives a 4-stage recommender — learned two-tower retrieval, a learned ranker, sequential modeling, and a path into generative retrieval with semantic IDs. An independent hard-constraint safety layer screens every candidate before it surfaces, recording why each was kept or excluded. Recall@K and NDCG evaluation gates every change across the full pipeline.
Two-Tower Retrieval · Learning to Rank (DLRM / DCN-v2) · Sequential Modeling (SASRec)
Rolling basis
team of 4 · 2 open
Academic AI
Production evaluation pipeline with rubric-aligned generative assessment and self-consistency verification. Retrieval-augmented feedback synthesis across configurable assessment criteria. 500+ documents per evaluation cycle, 3 institutional deployments, 60% overhead reduction.
LangGraph (Multi-Agent Orchestration) · Rubric-Aligned Generation · Self-Consistency Verification
Rolling basis
team of 5 · 1 open
Restaurant AI
Social restaurant discovery platform with visual collections, real-time group dining chat, and multi-agent personalization. 4 orchestrator-delegated specialist agents handle Yelp discovery, flavor profiling (6-dimensional taste vectors), beverage pairing, and budget analysis. Hybrid allergy filtering — keyword intersection confirmed by AI — runs as an independent safety gate before preference scoring across the full agent layer.
Multi-Agent Orchestration (Strands) · Preference Vector Matching (Multi-Dimensional Taste Modeling) · Hybrid Safety Filtering (Keyword + LLM Intersection)
Rolling basis
team of 3 · 2 open
Founded at BU · Systems backed by research · Volunteer-run
Collaborating with: Boston University · Boston Children's Hospital · Harvard Medical School · Cleveland Clinic
