Back to Details

bears-workflows

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

bears workflows

bears 工作流

Goal

目标

Provide experiment-selection and workflow guidance for PUDA workflows at bears, then load the correct experiment reference before execution.
为bears的PUDA工作流提供实验选择与工作流指导，然后在执行前加载正确的实验参考资料。

Critical Rule

重要规则

If you are unsure which experiment matches the user's task, ask the user before proceeding.
Do not assume.
如果你不确定哪个实验匹配用户的任务，请询问用户后再继续。
切勿自行假设。

Experiment Capabilities and When to Use

实验能力与适用场景

Colour Mixing Optimization (
colour-mixing-opt
)

颜色混合优化（
colour-mixing-opt
）

Use for iterative RGB colour mixing to match a target colour via RMSE minimization.
Capabilities:
  • Automated liquid handling on Opentrons OT-2 to mix R, G, B dye volumes
  • Camera capture of mixed colour after each dispensing step
  • VLM-based image processing and ROI extraction for per-well RGB measurement
  • RMSE calculation between mixed and target colour
  • Bayesian Optimization (BO) or LLM-driven suggestion of next volume ratios
  • Iterative protocol generation and execution until stop condition is reached
  • Per-iteration report generation (volumes, RGB, RMSE, next suggestion)
Use this experiment when:
  • The user wants to mix colours to match a target RGB
  • The task involves optimizing volume ratios of dyes to minimize colour error
  • The user mentions colour mixing, RMSE, BO, or LLM-guided liquid handling
Runner script: 
scripts/run_colour_mixing.py
  • End-to-end experiment runner; edit the config block at the top to change parameters
  • Set 
    ROBOT_IP
    to the OT-2 IP address in 
    .env
    for fully automated protocol execution via HTTP API
  • Set 
    OPENROUTER_API_KEY
    environment variable before running
  • Outputs: generated protocols in 
    protocols/
    , corrected images in 
    images/
    , live report in 
    reports/report.md
Before running:
  • Refer to: colour-mixing-opt
  • See optimization details: optimization.md
  • See image processing details: image-processing.md
  • Optimizer classes: scripts/optimizers.py
  • RMSE utility: scripts/rmse.py
  • Image processing pipeline: scripts/image_processing.py
适用于通过RMSE最小化实现迭代式RGB颜色混合以匹配目标颜色的场景。
能力：
  • 在Opentrons OT-2上自动处理液体，混合R、G、B染料体积
  • 每次分液步骤后拍摄混合颜色的照片
  • 基于VLM的图像处理和ROI提取，用于测量每个孔的RGB值
  • 计算混合颜色与目标颜色之间的RMSE
  • 通过贝叶斯优化（BO）或LLM驱动的建议确定下一组体积比例
  • 生成并执行迭代协议，直到满足停止条件
  • 生成每一轮迭代的报告（体积、RGB值、RMSE、下一次建议）
在以下场景使用本实验：
  • 用户希望混合颜色以匹配目标RGB值
  • 任务涉及优化染料体积比例以最小化颜色误差
  • 用户提到颜色混合、RMSE、BO或LLM引导的液体处理
运行脚本：
scripts/run_colour_mixing.py
  • 端到端实验运行器；编辑顶部的配置块以更改参数
  • 在
    .env
    文件中设置
    ROBOT_IP
    为OT-2的IP地址，通过HTTP API实现全自动协议执行
  • 运行前设置
    OPENROUTER_API_KEY
    环境变量
  • 输出：生成的协议存储在
    protocols/
    目录，校正后的图像存储在
    images/
    目录，实时报告存储在
    reports/report.md
运行前准备：
  • 参考：colour-mixing-opt
  • 查看优化细节：optimization.md
  • 查看图像处理细节：image-processing.md
  • 优化器类：scripts/optimizers.py
  • RMSE工具：scripts/rmse.py
  • 图像处理流水线：scripts/image_processing.py

Viscosity Optimization (
viscosity-optimization
)

粘度优化（
viscosity-optimization
）

Use for iterative tuning of Opentrons OT-2 liquid handling parameters for viscous fluids using gravimetric feedback.
Capabilities:
  • Automated protocol generation and execution on Opentrons OT-2
  • Concurrent gravimetric data collection from a mass balance (4 Hz) during each run
  • Automatic data processing: outlier removal, phase slicing, normalisation
  • Transfer error calculation (signed and absolute, in µL)
  • Bayesian Optimization (LCB or EI) or LLM-driven suggestion of next protocol parameters
  • Optimizable parameters: flow rates, delays, aspirate/dispense offsets
  • Per-iteration report generation (params, signed error, absolute error)
Use this experiment when:
  • The user wants to improve pipetting accuracy for viscous or non-water liquids
  • The task involves tuning flow rate, delay, or offset parameters to minimize transfer error
  • The user mentions gravimetric calibration, balance feedback, or viscosity optimization
  • The user mentions BO, LCB, EI, or LLM-guided pipetting parameter optimization
Before running:
  • Refer to: viscosity-optimization
适用于利用重量反馈迭代调整Opentrons OT-2的液体处理参数以适配粘性流体的场景。
能力：
  • 在Opentrons OT-2上自动生成并执行协议
  • 每次运行期间从天平（4 Hz）同步收集重量数据
  • 自动数据处理：异常值移除、阶段分割、归一化
  • 计算转移误差（有符号和绝对值，单位为µL）
  • 通过贝叶斯优化（LCB或EI）或LLM驱动的建议确定下一组协议参数
  • 可优化参数：流速、延迟、吸液/分液偏移量
  • 生成每一轮迭代的报告（参数、有符号误差、绝对误差）
在以下场景使用本实验：
  • 用户希望提高粘性或非水液体的移液精度
  • 任务涉及调整流速、延迟或偏移量参数以最小化转移误差
  • 用户提到重量校准、天平反馈或粘度优化
  • 用户提到BO、LCB、EI或LLM引导的移液参数优化
运行前准备：
  • 参考：viscosity-optimization

Selection Workflow

选择工作流

  1. Parse user intent and identify the experiment type.
  2. Match intent to the experiment capabilities above.
  3. If experiment selection is unclear or ambiguous, ask the user and wait for confirmation.
  4. Load the corresponding reference file.
  5. Proceed with the experiment workflow only after the experiment is confirmed.
  1. 解析用户意图，确定实验类型。
  2. 将意图与上述实验能力匹配。
  3. 如果实验选择不明确或存在歧义，询问用户并等待确认。
  4. 加载对应的参考文件。
  5. 仅在实验确认后继续执行实验工作流。

Output Guidance

输出指导

When answering experiment-selection questions:
  • State the recommended experiment and a one-line reason tied to its capability.
  • If uncertain, ask a direct clarification question instead of guessing.
回答实验选择相关问题时：
  • 说明推荐的实验，并给出与其能力相关的一句话理由。
  • 如果不确定，直接询问澄清问题，不要猜测。

Critical Rules

重要规则

  1. Always ask for all required inputs (target colour, thresholds, limits, deck layout) before starting any experiment.
  2. Ask the user for the OT-2 robot IP address before running, and set it as 
    ROBOT_IP
    in 
    .env
    .
  3. Ask the user for the OpenRouter API key if not already set in the environment.
  4. Invoke puda-memory after every protocol creation and run to keep 
    experiment.md
    current.
  5. Opentrons protocols must always end with no tip attached to any pipette.
  6. Ask user if unsure — do not assume.
  1. 在开始任何实验之前，务必询问所有必要的输入信息（目标颜色、阈值、限制、甲板布局）。
  2. 运行前询问用户OT-2机器人的IP地址，并在
    .env
    中设置为
    ROBOT_IP
    。
  3. 如果环境中未设置
    OpenRouter API密钥
    ，请询问用户。
  4. 在每次协议创建和运行后调用puda-memory，以保持
    experiment.md
    内容最新。
  5. Opentrons协议结束时，所有移液器必须处于无吸头状态。
  6. 不确定时询问用户——切勿自行假设。