Tigerfish Prompt Engineering and Data Labeling. The human touch.

In business since 1989, we’ve learned a few things. Accuracy. Meeting a deadline. How to decipher and optimize complex projects. 

Here’s our secret

There’s no substitute for experience. Everything we know we’ve learned on the job. Assembling the team. Assigning the tasks. Delivering results.

Put our experience to work for you. You’ll have the benefit of a personal project manager, context engineers with expertise in the field, and a customizable platform.

Tell us what you need and we’ll get it right.

You guys rock! Thank you!

SS, Apple.com

I love Tigerfish.

AC, Vice President, BlackRock

Tigerfish.  The word on time.

You have a winning AI engine. Keep that engine humming with the right tools and precise calibration.  Turn to Tigerfish for expert prompt engineering and RLHF services

Prompt engineering is how we choreograph the conversation in real time—designing system prompts, roles, and examples. RLHF is how we change what the model wants to do—using expert feedback and reward models to retrain its instincts.

With over three decades in business, Tigerfish is on it.

Pattern-based prompting tuned to your domain, brand voice, and desired UX.

Trust Tigerfish for

  • Zero-Shot Prompting: Design prompts that enable you to perform a task without any specific examples, relying solely on pre-existing knowledge.
  • One-Shot Prompting: Provide your model with one example to guide its output.
  • Few-Shot Prompting: Include a small number of examples to help your model learn a pattern or style. 
  • Pattern-Based Tuning: Create custom prompt structures to align responses with a particular domain, brand voice, and user experience.

Fast, focused, and flawless.

W.L.
AT&T Labs

Simplify complex decisions in finance, legal, security, and other operations.

Trust Tigerfish for

  • Chain-of-Thought (CoT) Engineering: Prompts that encourage your model to "think step-by-step," improve performance on complex reasoning, mathematical problems, and nuanced decision-making.
  • Logical Scaffolding: Structural frameworks guide the model through multi-layered tasks.
  • Structured Problem-Solving: Break down high-level objectives into manageable sub-tasks, aiming to turn abstract goals into consistent, executable AI workflows.
  • Prompt Sequencing and Refinement: Iterative prompting strategies refine AI outputs and improve the relevance and accuracy of responses for challenging queries.

The quality of your work and your attention to detail has made my job so much easier. Thank you!

J.J.
Hewlett Packard

Transform static models into dynamic, data-driven systems.

Trust Tigerfish for

  • Prompt Chaining: Link multiple interactions into a single workflow, where the output of one step informs the next to handle complex, multi-stage processes.
  • Prompt Architectures: High-level structural blueprints ensure prompts are scalable, modular, and easily integrated into existing software stacks.
  • Retrieval-Augmented Generation (RAG): Private, real-time data sources provide accurate responses grounded in specific documents and knowledge bases.
  • Contextual Data Integration: Reduce inaccuracies and ensure outputs are relevant to the unique operational environment.

Lightning-fast response times and genuine care for our success.

H.H.
Genentech

Alignment with reality is your stock in trade. Make sure you get it right.

Trust Tigerfish for

  • Claim Validation. We interpret and assess information from multiple sources to enhance nuance, and resolve conflicting information.
  • Structured Verification Protocols. We check citations and flag unsupported or contradicted claims.
  • Clear Reporting. We highlight specific factual errors, missing support, or contradictory evidence.
  • Meticulous Verification. Get the benefit of 35 years of fine-tuning.

Your team's dedication to accuracy is unmatched, delivering flawless results well before our deadline!

S.J.
France Telecom R & D

Get the tone right. Everything else will follow. 

Trust Tigerfish for

  • Expertise in Linguistic Nuance. We understand style and persona.
  • Creative Task Design. Clear and comprehensive instructions guide Tigerfish annotators. 
  • Brand Alignment. Understanding brand and voice enables us to create actionable criteria.
  • Feedback Cycles. Iterative feedback allows us to refine model attributes.
  • Attribute-Specific Rater Pools. We select and train evaluators with specific expertise (humor, specific cultural contexts, etc.).

Amazing work! I'm impressed with your research and thoroughness.

JL
Google

A useful helper is honest, harmless, and concise. 

Trust Tigerfish for

  • Superior Guideline Interpretation. Tigerfish evaluators apply nuanced guidelines, leading to reliable preference signals.
  • Inter-Annotator Agreement (IAA). Accurate calibration and robust quality control result in exceptional IAA scores.
  • Nuance Capture Expertise. Subtle differences in tone, style, safety, and helpfulness are critical for high-fidelity reward models.
  • Diverse Perspective Integration. Diverse viewpoints help mitigate subjective bias.
  • Efficient & Scalable Workflows. We efficiently manage large-scale preference data collection without sacrificing quality or consistency.
  • Clear Rationale Capture. Tigerfish annotators document their reasoning for analysis and model understanding.

Everything went well (as usual!) Thanks for the great work.

JR
Wells Fargo Funds Management

Diverse, accurate, meticulously crafted prompts make all the difference. 

Trust Tigerfish for

  • Creative Prompt Generation. A wide range of prompts – simple to complex, covering diverse topics and instruction types – is crucial for robust SFT.
  • Response Crafting. Clear, unambiguous, accurate "ideal responses" serve as high-quality exemplars.
  • Domain-Specific Knowledge Application. Tigerfish writers create contextually appropriate instruction pairs for specialized domains.
  • Scalability for Large Datasets. Expert project management and solid infrastructure lead to high-quality SFT datasets.

Once again you have really pulled through. I heard that you are the best and I can see for myself you are.

CC
Cisco

Deliver results in style. 

Trust Tigerfish for

  • Deep Analysis. We identify logical fallacies, factual inaccuracies, and stylistic inconsistencies.
  • Clear & Actionable Feedback. Tigerfish evaluators provide a narrative analysis of model strengths and vulnerabilities. 
  • Subject Matter Expertise. Annotators with relevant domain knowledge provide context-aware and technically accurate critiques.
  • Constructive Rewriting & Editing. When called for, Tigerfish editors suggest helpful rewrites.
  • Consistent Application. Critiques are applied consistently against established rubrics and standards.

From start to finish the process is seamless and that sure makes my life a lot easier!

HT
Intel

If you can't customize it, you won't get what you need.

Trust Tigerfish for

  • Flexibility & Adaptability. Our "built-from-scratch" experience and operational agility allow us to adapt to varied data types.
  • Collaborative Design. We design effective annotation tasks, guidelines, and workflows.
  • Prototyping. New designs are tested on a small scale to gather feedback before full-scale deployment.
  • Cross-Functional Expertise. Tigerfish brings together experts in linguistics, AI ethics, project management, and specific subject matters.

"WOW…now that is some speedy service! Yep, that’s what we love so much about you guys. You take good care of us.

KT
Intel

Fuzziness won't cut it. You need concrete suggestions to fine-tune your model.

Trust Tigerfish for

  • Strong Writing & Editing. Tigerfish writers know their craft.
  • Constructive Feedback. We provide clear, actionable suggestions.
  • Output Alignment. Rewrites and suggestions align with your goals for tone, style, and quality.
  • Enhanced Communication and Accuracy. Our processes help fine-tune your model. 

Tremendous work, and excellent customer service. It's a pleasure to work with you!

KG
Intel

Audited. Verified. Triple checked for accuracy.

Always on time, always accurate, and always delightful to talk to—the gold standard of service.

S.P.
Aruba Networks

Why Tigerfish?

Tigerfish has been in business since 1989.  Known to our customers as dependable, intelligent, and easy to work with, we have built a reputation based upon a commitment to excellence and attention to detail.  

Let us put our team to work for you. You'll enjoy the benefits of:

  • The Right Experts for the Job
  • Open-Book Collaboration
  • Iterative Technical Roadmaps
  • Real-Time Status Updates
  • Cost Transparency
  • Dedicated Project Managers
  • Custom-Built Foundations
  • Rigorous Bias & Safety Guardrails
  • Complete IP Ownership
  • Future-Proof Logic
  • Satisfaction Guaranteed

The following studies inform our work.

  • From Prompt Engineering to Prompt Science with HITL

    Chirag Shah, Maryam Amirizaniani, and Elizabeth Snell Okada
    University of Washington

    Introduces a systematic “Prompt Science” methodology inspired by qualitative coding, involving a multi-phase human verification process to remove individual bias and ensure that templates are objective and replicable.

    Read more

  • RLTHF: Targeted Human Feedback for Efficient Alignment

    S. Garg, V. Perot, and L. Dixon
    Microsoft Research

    A hybrid framework identifies samples where reward models are most likely to fail. By targeting these for human correction, full alignment quality was achieved.

    Read more

  • CoTAL: Human-in-the-Loop Prompt Engineering for Education

    Clayton Cohn, Ashwin T.S., and Gautam Biswas
    Vanderbilt University

    Formative Assessment Scoring allows educators to refine prompt logic in real time, ensuring AI-generated feedback aligns with complex pedagogical standards.

    Read more

  • ROPE: Training Humans for Better Prompt Engineering

    Qianou Ma, Weirui Peng, and Ken Koedinger
    Carnegie Mellon University

    This study explores training humans to provide more effective feedback, identifying interventions that lead to 30% faster convergence in model alignment during the RLHF phase.

    Read more

  • The Rhetorical Situation in Prompt Design

    J. Hadi, L. S. Silverstein, and R. Thompson
    New York University / Springer Nature

    Framing prompts as “rhetorical situations” provides a practical HITL implementation for content development that avoids the sterility of purely algorithmic decisions.

    Read more

  • Reward Model Misspecification and Robust RLHF

    J. Smith, R. Garcia, and A. Nguyen
    Oxford University / Alan Turing Institute

    An algorithm that reduces variance in human estimators, helping RLHF systems favor human-preferred responses 80% more often.

    Read more

  • Improving RLHF via Language-Based Feedback

    T. Rajpurohit, A. Kalyan, and S. Chaudhari
    Princeton University

    Moving beyond 1-10 ratings, this study uses fine-grained language feedback. By replacing binary rankings with descriptive sentences, the model learns nuanced preferences, reducing model sycophancy.

    Read more

  • Safe RLHF: Balancing Helpfulness and Harmlessness

    J. Dai, X. Pan, and R. Sun
    UC Berkeley / Center for AI Safety

    Decoupling human feedback into “helpful” and “safe” dimensions allows researchers to train models that aren’t “refusal-happy” but strictly adhere to safety guardrails.

    Read more

  • Intrinsic Rewards for Multi-Turn Human Interaction

    S. Chaudhari, P. Aggarwal, and V. Murahari
    Princeton University

    The model is rewarded when its multi-turn responses lead to a human successfully completing a complex task, training for collaboration rather than just “correct” single answers.

    Read more

  • ProcessBench: Identifying Logic Errors via Human Audits

    B. Koopman, A. Nicolson, and S. Zhuang
    CSIRO (Australia) / University of Queensland

    This study uses human auditors to benchmark the “reasoning process” of an AI, and provides a toolkit for catching logic gaps where the AI hits the right answer for the wrong reasons.

    Read more

Precision balanced with such a friendly, supportive customer service team has been a game-changer.

R.D.
Jet Propulsion Laboratory

Resourceful, dependable, intelligent, friendly.

Attention to detail, rock solid infrastructure, exceptional reliability -- that's the vision that guided Adam Goldberg when he started Tigerfish more than thirty-five years ago. Since then, the company's growth has embodied Adam's principle that people excel in a friendly, supportive environment. After all, the secret to great work is great teamwork.

The Tigerfish Story
At first, Tigerfish was a one person operation...

Our Neighborhood

John Coltrane and Thelonious Monk played around the corner. So did Janis Joplin and Jerry Garcia. Joe DiMaggio married Marilyn Monroe in the local cathedral. Francis Ford Coppola edited The Godfather on our street. Lenny Bruce performed at the Purple Onion. Allen Ginsberg and Bob Dylan hung out at Lawrence Ferlinghetti's City Lights Books. Ellen DeGeneres got her start here. Dashiell Hammett was a regular at the Tosca Cafe. Robin Williams worked new material a few blocks away. Humphrey Bogart, Lauren Bacall, Alfred Hitchcock, Jimmy Stewart, Clint Eastwood, and Woody Allen filmed here.

And for over thirty years San Francisco’s North Beach has been home to Tigerfish. 

Call us up. There are some people we’d like you to meet.

From start to finish, seamless and professional, arriving early and exceeding every benchmark.

A.J.
General Electric

A solid reputation, built on a commitment to excellence.

From earth science to space exploration, from historical archive to economic forecast, from print to air, courtroom to boardroom, Tigerfish has earned the trust of those who need it right the first time.

Our esteemed clients include:

Incredible service! You caught every nuance of our request and delivered ahead of schedule.

J.D.
Microsoft Co.

We'd love to hear from you.

Fill out the form below and we'll be in touch.

I am interested in the following services:

Your customer support is a masterclass in efficiency and kindness, making every interaction a total breeze.

B.N.
Accenture

Careers

What's at the heart of Tigerfish? A team of brilliant, task-oriented, friendly people devoted to careful listening, open communication, and solving problems creatively.

Tigerfish is currently hiring for the following positions:

Data labeler

Intelligent writing, lexicographical expertise, first rate research -- if this is you, we'd like to hear from you.

For more than thirty years, Tigerfish has built a successful business by working with freelancers on the basis of mutual respect, good pay, and flexible hours. 

If you have an advanced degree and a talent for evaluation, join Tigerfish!

To apply, send a cover letter and your resume to: careers@tigerfish.ai